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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16375
    Prev
    Next
    INDEX
    Explanations

    statements indicating existence or presence of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    RefNanny
    -0.35
     Kruse
    -0.33
     prevenção
    -0.32
     lendemain
    -0.31
     Helf
    -0.31
     بهتر
    -0.30
    BindingSource
    -0.29
    ContentLoaded
    -0.29
    xase
    -0.29
     voluntarios
    -0.29
    POSITIVE LOGITS
    addGap
    0.69
    𑄮
    0.67
    𑄨
    0.66
    𑄢
    0.66
    addPreferredGap
    0.65
    <unused43>
    0.65
    𑄠
    0.65
    𑄥
    0.65
    <unused3>
    0.65
    <unused8>
    0.65
    Activations Density 0.064%

    No Known Activations