© 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. 11-GEMMASCOPE-RES-16K
    11. 5479
    Prev
    Next
    INDEX
    Explanations

    actions or initiatives aimed at improving or advancing scientific research and technology for environmental and health benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.69
    WriteBarrier
    -0.65
    
    -0.60
     ddelweddau
    -0.58
    +#+
    -0.56
     demografica
    -0.56
     ModelExpression
    -0.55
    "]);
    -0.55
    lgari
    -0.53
    帖最后由
    -0.53
    POSITIVE LOGITS
     critical
    0.37
     sense
    0.36
    kolwiek
    0.36
     every
    0.35
     aldri
    0.35
     kritis
    0.34
     wyt
    0.33
    culas
    0.33
     strategis
    0.33
     both
    0.33
    Activations Density 0.749%

    No Known Activations