© 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. 3-GEMMASCOPE-RES-16K
    11. 12594
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific function or callback references in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.92
     ſtate
    -0.91
     purpoſe
    -0.89
     itſelf
    -0.88
    ſelf
    -0.84
     Reſ
    -0.82
     ſeveral
    -0.82
     fevere
    -0.81
     STEVEN
    -0.80
     ftate
    -0.79
    POSITIVE LOGITS
    cb
    2.70
    CB
    2.46
     CB
    2.39
     cb
    2.31
    Cb
    1.74
     Cb
    1.58
    cbs
    1.17
    CBM
    1.02
     cbs
    1.00
    cbf
    1.00
    Activations Density 0.084%

    No Known Activations