© 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. 8997
    Prev
    Next
    INDEX
    Explanations

    closing braces and brackets in JSON-like structures

    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
     للمعارف
    -0.91
    elemField
    -0.88
    حياتها
    -0.81
    bootstrapcdn
    -0.81
     houſe
    -0.74
    Izvori
    -0.73
    principalColumn
    -0.72
    حياته
    -0.70
     Shakspeare
    -0.70
     Venise
    -0.69
    POSITIVE LOGITS
     дописавши
    0.71
    onOptions
    0.59
    Flu
    0.58
    FLU
    0.57
     المق
    0.57
     márm
    0.56
    勃
    0.55
    endforeach
    0.55
     }^{[
    0.55
    flu
    0.55
    Activations Density 0.068%

    No Known Activations