© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 6752
    Prev
    Next
    INDEX
    Explanations

    patterns of numbers or code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.77
    請繼續往下閱讀
    -0.75
    
    -0.69
    ImageContext
    -0.69
     unknownFields
    -0.66
    انيف
    -0.66
    EndInit
    -0.65
     Biôgrafia
    -0.65
     HasFactory
    -0.65
     resourceCulture
    -0.64
    POSITIVE LOGITS
    ↵
    1.37
    ↵↵↵
    0.78
    ↵↵
    0.78
    0.72
    ↵↵↵↵
    0.72
    </strong>
    0.69
    ↵↵↵↵↵
    0.67
    </h3>
    0.66
    </b>
    0.66
    <eos>
    0.61
    Activations Density 0.131%
    No Known Activations