© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15659
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors related to qualities and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words that describe sharpness, brightness, or quickness (including adjectives like "bright," "sharp," "quick," and "tight").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    adjectives describing something as vivid, intense, or having a strong quality (particularly "bright", "sharp", "tight", and "quick").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    vivid, high-intensity descriptive modifiers—especially those conveying sharpness/tightness, brightness, speed, or degree, often appearing in set phrases.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATION
    -0.38
     насељу
    -0.36
     getHeight
    -0.35
     bere
    -0.34
    NodeInfo
    -0.34
    Weiterlesen
    -0.31
     ura
    -0.31
    ITIES
    -0.31
    どく
    -0.31
    UNDA
    -0.31
    POSITIVE LOGITS
    est
    0.79
     enough
    0.79
    ened
    0.77
    Enough
    0.71
    ish
    0.70
    ening
    0.69
    enough
    0.69
    ness
    0.68
    nesses
    0.61
    Xna
    0.61
    Activations Density 0.413%

    No Known Activations