© 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. 38-GEMMASCOPE-RES-16K
    11. 7329
    Prev
    Next
    INDEX
    Explanations

    scientific procedures and techniques related to biological research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.35
     zob
    -0.35
    tagHelperRunner
    -0.34
    帖最后由
    -0.34
    FieldNumber
    -0.32
    SourceChecksum
    -0.31
    Captor
    -0.30
     démocratie
    -0.29
    ukunft
    -0.29
    mybatisplus
    -0.29
    POSITIVE LOGITS
     done
    3.47
    done
    2.98
     Done
    2.86
    Done
    2.78
     performed
    2.56
     DONE
    2.38
     Performed
    2.20
     conducted
    2.13
    performed
    2.13
    DONE
    2.09
    Activations Density 2.061%

    No Known Activations