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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 45430
    Prev
    Next
    INDEX
    Explanations

    references and citations within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     snippetHide
    -0.65
    expandindo
    -0.60
     betweenstory
    -0.59
     tartalomajánló
    -0.59
     estekak
    -0.59
    TypedDataSet
    -0.59
    EndContext
    -0.56
    __(/*!
    -0.56
    GraphicsUnit
    -0.56
    WithIOException
    -0.56
    POSITIVE LOGITS
    JsonPropertyName
    0.39
     juuri
    0.38
     Cristóbal
    0.38
    genöss
    0.37
     Absatz
    0.36
    었습니다
    0.36
     Meksika
    0.36
     näytte
    0.36
    ylül
    0.35
    giques
    0.35
    Activations Density 0.517%

    No Known Activations