© 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. 18-GEMMASCOPE-RES-16K
    11. 6425
    Prev
    Next
    INDEX
    Explanations

    terms related to leadership and management in a professional context

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

    ending in "ility", "style", "sis", "sion", or "ately"

    np_acts-logits-general · gemini-2.0-flash

    business, political, and scientific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.77
    __;
    -0.76
    ;*/
    -0.75
    */;
    -0.74
    uxxxx
    -0.73
    PostExecute
    -0.72
    <bos>
    -0.69
     */;
    -0.69
    .";
    -0.68
    FTFY
    -0.67
    POSITIVE LOGITS
    </h2>
    0.79
    </h4>
    0.75
    </h3>
    0.73
    Климат
    0.59
     []:
    0.56
    </h5>
    0.54
    ↵↵
    0.53
    </strong>
    0.51
    ?
    0.51
    setVerticalGroup
    0.50
    Activations Density 0.300%

    No Known Activations