© 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. 15300
    Prev
    Next
    INDEX
    Explanations

    specific DOI (Digital Object Identifier) references in scholarly publications

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

    Percent signs and associated formatting

    np_acts-logits-general · gemini-2.0-flash

    URL encoding and 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
    ]").
    -0.61
    ,'"
    -0.58
    '){
    -0.57
    </caption>
    -0.57
    ,’”
    -0.56
    ]");
    -0.56
    ))->
    -0.55
    ]').
    -0.55
    '))
    -0.54
    ']>;
    -0.54
    POSITIVE LOGITS
     %
    2.66
    %
    2.65
     '%
    1.92
    >%
    1.92
     (%
    1.91
    =%
    1.91
     "%
    1.90
    .%
    1.89
    :%
    1.86
    ,%
    1.84
    Activations Density 0.237%

    No Known Activations