© 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. 22-GEMMASCOPE-RES-16K
    11. 10049
    Prev
    Next
    INDEX
    Explanations

    start tokens and usage of special characters in programming or script context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text following punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    lunch break

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -1.25
    ^(@)
    -1.18
    )";
    -1.17
    \<^
    -1.16
     $_"
    -1.16
     שוליים
    -1.15
    !")
    -1.15
    >\<^
    -1.14
    .³
    -1.14
    .",
    -1.13
    POSITIVE LOGITS
      
    0.89
    ↵
    0.85
     ->
    0.81
     */
    0.74
    ...
    0.74
    ..
    0.73
    </em>
    0.72
    )
    0.69
    */
    0.68
     doesn
    0.67
    Activations Density 0.285%

    No Known Activations