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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1429
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

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

    Units of measurement or symbols

    np_acts-logits-general · gemini-2.0-flash

    ditto

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    parsedMessage
    -0.86
    verifyException
    -0.86
    OGND
    -0.77
     autorytatywna
    -0.75
    aarrggbb
    -0.74
     transfieras
    -0.73
     kasarigan
    -0.72
     defaultstate
    -0.69
    inSlope
    -0.68
    TagNumber
    -0.68
    POSITIVE LOGITS
     similarly
    0.38
    同じく
    0.36
     ditto
    0.36
    same
    0.34
    Likewise
    0.33
     same
    0.33
    ditto
    0.33
     likewise
    0.32
     Likewise
    0.30
     SAME
    0.30
    Activations Density 0.716%

    No Known Activations