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. 12302
    Prev
    Next
    INDEX
    Explanations

    numerical references typically associated with academic publications

    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
     صوتيه
    -0.57
    tanleria
    -0.50
     للاسماء
    -0.40
    \{\\
    -0.39
    GeoNames
    -0.38
    EditorBrowsable
    -0.34
     Chwiliwch
    -0.33
    <?>>
    -0.32
    bilir
    -0.32
    ])),
    -0.32
    POSITIVE LOGITS
     IBOutlet
    0.52
     GenerationType
    0.52
    UIControlState
    0.50
     month
    0.50
     collector
    0.48
     week
    0.48
     queſta
    0.48
     Jas
    0.47
     Finals
    0.47
    GeneratedCode
    0.47
    Activations Density 0.165%

    No Known Activations