© 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. 14167
    Prev
    Next
    INDEX
    Explanations

    keywords and patterns related to subscription topics in a programming or application context

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

    Code, tables, or bracketed references

    np_acts-logits-general · gemini-2.0-flash

    table formatting

    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
    ）』
    -0.80
    %;
    -0.78
     дописавши
    -0.78
     ';
    -0.77
    |
    -0.76
    `;
    -0.72
    /';
    -0.71
    '},
    -0.69
    =[];
    -0.69
    )]
    -0.68
    POSITIVE LOGITS
    ",
    1.83
    ")
    1.80
    」
    1.70
    "
    1.69
    ").
    1.61
    ");
    1.58
    ".
    1.53
    ";
    1.46
    ":
    1.38
    ."
    1.35
    Activations Density 1.129%

    No Known Activations