© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4943
    Prev
    Next
    INDEX
    Explanations

    programming and framework-specific annotations and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.74
    contentLoaded
    -0.72
     ويكيميديا
    -0.64
    DebuggerStep
    -0.63
    fetchall
    -0.62
     πάντα
    -0.62
     lắm
    -0.61
    CodedInputStream
    -0.60
    zerland
    -0.59
     FontWeight
    -0.59
    POSITIVE LOGITS
    {@
    0.96
    ValueStyle
    0.94
    EIF
    0.91
    bitField
    0.86
    Portale
    0.85
    原始内容存档于
    0.85
    nullable
    0.84
    awtextra
    0.79
    بوابة
    0.77
    mstyle
    0.76
    Activations Density 0.004%

    No Known Activations