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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 57324
    Prev
    Next
    INDEX
    Explanations

    events related to legal proceedings and outcomes

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

    End-of-clause or end-of-sentence tokens, often punctuation marks or transitional phrases that connect one thought to the next.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    OGND
    -0.60
    Autoritní
    -0.52
     يتيمه
    -0.51
     tartalomajánló
    -0.49
    ⓧ
    -0.48
     kasarigan
    -0.48
    Datuak
    -0.47
     Signalez
    -0.46
    AnchorStyles
    -0.45
    хівовано
    -0.45
    POSITIVE LOGITS
    ksesta
    0.40
    CodedInputStream
    0.39
    interopRequire
    0.39
    upné
    0.38
    SerializedSize
    0.38
    writeFieldEnd
    0.38
    principalTable
    0.38
     озе
    0.37
    parsedMessage
    0.37
    appBar
    0.36
    Activations Density 0.187%

    No Known Activations