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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4209
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to performance metrics and demographic representations

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

    numerical comparisons indicating something is smaller or lower than a threshold or expected value.

    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
     Comprometido
    -0.44
     Higher
    -0.43
     higher
    -0.43
    越大
    -0.43
    GeneratedMessage
    -0.43
    Higher
    -0.41
    以上
    -0.41
    Longer
    -0.41
     LARGE
    -0.40
    )>=
    -0.40
    POSITIVE LOGITS
     barely
    1.29
     negligible
    1.11
    わずか
    1.06
     tiny
    1.03
     meager
    0.98
     paltry
    0.98
     scant
    0.98
     meagre
    0.94
     hardly
    0.94
    tiny
    0.93
    Activations Density 1.052%

    No Known Activations