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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104725
    Prev
    Next
    INDEX
    Explanations

    terms related to micronutrients and their deficiencies

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

    Specialized terminology and syntax elements from scientific, mathematical, and technical documents that carry domain-specific meaning.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.69
     surla
    -0.68
    Derbyniad
    -0.62
    iettivo
    -0.55
    BagConstraints
    -0.52
    ConstraintMaker
    -0.52
     հղումներ
    -0.50
     esternos
    -0.49
    BagLayout
    -0.49
     mergeFrom
    -0.48
    POSITIVE LOGITS
     traditionnel
    0.46
     tradicionales
    0.42
    เพลง
    0.41
    传统的
    0.41
     conocimientos
    0.41
     clásicos
    0.41
     clássico
    0.40
     vœux
    0.40
     سنتی
    0.40
     rurales
    0.40
    Activations Density 0.243%

    No Known Activations