Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15548
    Prev
    Next
    INDEX
    Explanations

    parameters and configuration settings in technical or programming contexts

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

    Parameters including capacity and bank

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     sebou
    -0.30
     storici
    -0.29
     exé
    -0.28
    역
    -0.28
     bug
    -0.28
     emiti
    -0.28
     amarilla
    -0.27
     bleue
    -0.26
     inconnu
    -0.26
    viewBox
    -0.26
    POSITIVE LOGITS
     يتيمه
    0.86
     resourceCulture
    0.79
    AxisAlignment
    0.68
     collisions
    0.67
     Bucket
    0.66
     hashing
    0.65
     HASH
    0.65
     bucket
    0.64
     hash
    0.64
    bucket
    0.63
    Activations Density 0.250%

    No Known Activations