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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12510
    Prev
    Next
    INDEX
    Explanations

    metadata fields and values in a structured data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.48
    gameserver
    -0.48
    ViewImports
    -0.46
     surla
    -0.46
    новниш
    -0.45
    TableField
    -0.43
    yarnpkg
    -0.43
    Aktualisiert
    -0.43
     honoured
    -0.41
     recognise
    -0.40
    POSITIVE LOGITS
     aventures
    0.39
    </thead>
    0.38
     sleigh
    0.37
    
    0.35
    dataclass
    0.35
     pinulongan
    0.35
     Faso
    0.34
    TRX
    0.34
    ...');
    0.33
    centralwidget
    0.32
    Activations Density 2.268%

    No Known Activations