© 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. 4494
    Prev
    Next
    INDEX
    Explanations

    concepts related to problem-solving and adaptation in various contexts

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

    words related to thriving, flourishing, or succeeding despite challenges or constraints.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    ően
    -0.48
    ganza
    -0.39
    neh
    -0.37
    訟
    -0.36
    aterally
    -0.36
    wnie
    -0.35
    geer
    -0.34
    haustible
    -0.33
    minecraftforge
    -0.33
    互联网档案馆
    -0.33
    POSITIVE LOGITS
     amid
    2.03
     amidst
    2.02
     Amid
    1.75
    Amid
    1.68
    amid
    1.48
     midst
    1.19
     surrounded
    1.07
     against
    0.99
     under
    0.97
    在这种
    0.91
    Activations Density 0.598%

    No Known Activations