Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5680
    Prev
    Next
    INDEX
    Explanations

    non-standard or unconventional code structures and patterns

    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
     שוליים
    -0.88
    antMatchers
    -0.80
     Lure
    -0.72
    rawDesc
    -0.69
    Sumber
    -0.68
     Hagen
    -0.68
    WriteAttribute
    -0.67
    Cyfeiriadau
    -0.67
    Fisch
    -0.67
    حياته
    -0.65
    POSITIVE LOGITS
    nlm
    0.69
    ↵↵
    0.68
     AssemblyProduct
    0.68
     }</
    0.66
    }}}}
    0.66
    </table>
    0.65
     Paused
    0.63
    .)}
    0.62
    }")
    0.61
     الاطلاع
    0.61
    Activations Density 0.107%

    No Known Activations