© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 430
    Prev
    Next
    INDEX
    Explanations

    punctuation and exclamatory expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?,?,
    -0.82
    ```
    -0.78
     Sutton
    -0.77
     Placer
    -0.77
    fromUtf
    -0.77
    \.
    -0.76
     RNG
    -0.75
    help
    -0.73
     onOptions
    -0.73
     TestBed
    -0.72
    POSITIVE LOGITS
    !!!
    0.99
    !!!"
    0.96
    ¡¡
    0.93
    !!!!!
    0.89
    !!!!
    0.86
    !!"
    0.84
    !!
    0.83
     !!!
    0.83
    !!!”
    0.78
     ¡¡
    0.78
    Activations Density 0.103%

    No Known Activations