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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75140
    Prev
    Next
    INDEX
    Explanations

    phrases that include the symbol "+" indicating addition or enhancement

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

    words connected by plus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     This
    -0.33
     They
    -0.31
    SourceChecksum
    -0.30
     pasado
    -0.30
     earlier
    -0.29
     Young
    -0.28
    OfDay
    -0.27
     These
    -0.27
     arbre
    -0.27
     ihre
    -0.27
    POSITIVE LOGITS
    <unused79>
    0.93
    <unused41>
    0.93
    <unused8>
    0.93
    [@BOS@]
    0.93
    <unused23>
    0.93
    <unused28>
    0.93
    <unused52>
    0.93
    <unused74>
    0.93
    <pad>
    0.92
    <unused3>
    0.92
    Activations Density 0.069%

    No Known Activations