© 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. 3-GEMMASCOPE-RES-16K
    11. 8111
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience and emotional reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.92
    RenderAtEndOf
    -0.81
     indígen
    -0.79
     gyhoeddwyd
    -0.79
    ruptedException
    -0.79
    parsedMessage
    -0.77
     Majefty
    -0.73
     témoig
    -0.73
     vooz
    -0.73
    ロウィン
    -0.72
    POSITIVE LOGITS
    Always
    0.54
     always
    0.54
    always
    0.52
     Always
    0.51
    ,
    0.46
     Siempre
    0.44
     siempre
    0.43
     всегда
    0.41
     ALWAYS
    0.41
    Sometimes
    0.41
    Activations Density 0.287%

    No Known Activations