© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2267
    Prev
    Next
    INDEX
    Explanations

    references to methods and procedures in scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.67
    httphttps
    -0.66
    LookAnd
    -0.56
     estekak
    -0.53
    findpost
    -0.51
    
    -0.50
    ValueStyle
    -0.48
    TRAILING
    -0.47
    帖最后由
    -0.44
    flage
    -0.43
    POSITIVE LOGITS
    Tembelea
    0.49
    PerformLayout
    0.47
    DispatchToProps
    0.44
     Италијани
    0.44
    MessageOf
    0.41
    HomeAsUpEnabled
    0.41
     asamblea
    0.40
     للمعارف
    0.39
    keyColumn
    0.38
    ToListAsync
    0.38
    Activations Density 0.663%

    No Known Activations