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. 51784
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific or technical processes and structures

    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
    DockStyle
    -0.72
     հղումներ
    -0.64
    InSection
    -0.61
    bootstrapcdn
    -0.61
     CreateTagHelper
    -0.60
    makeConstraints
    -0.56
    extAlignment
    -0.55
    ConstraintMaker
    -0.54
    LayoutStyle
    -0.52
    tagHelperRunner
    -0.49
    POSITIVE LOGITS
     naturlig
    0.39
     gjerne
    0.36
    banks
    0.33
     Budi
    0.33
     Bekasi
    0.33
     manqué
    0.33
     lits
    0.33
     Banken
    0.33
    amını
    0.32
     Banks
    0.32
    Activations Density 0.082%

    No Known Activations