© 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. 7-GEMMASCOPE-RES-16K
    11. 2910
    Prev
    Next
    INDEX
    Explanations

    references to notable observations or remarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     id
    -0.77
    {{$
    -0.74
     ID
    -0.72
    ftagPool
    -0.70
     يتيمه
    -0.68
     I
    -0.67
     Id
    -0.67
     i
    -0.66
    LEncoder
    -0.66
    getColumnIndex
    -0.65
    POSITIVE LOGITS
    remarks
    1.67
     Remarks
    1.42
    Remarks
    1.42
     remarks
    1.37
     remark
    1.35
    remark
    1.32
     Remark
    1.25
     REMARKS
    1.19
    Remark
    1.18
     Theſe
    1.17
    Activations Density 0.078%

    No Known Activations