© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13838
    Prev
    Next
    INDEX
    Explanations

    headings related to programming concepts, specifically constructors and methods in code documentation

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

    HTML code related to method or constructor summaries/details

    np_acts-logits-general · gemini-2.0-flash

    HTML section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ”,
    -1.57
    "],
    -1.35
    ",
    -1.35
    ”),
    -1.32
    "])
    -1.28
    ”,
    -1.24
    ”).
    -1.23
    <eos>
    -1.20
    "),
    -1.13
    ”。
    -1.12
    POSITIVE LOGITS
    </h3>
    3.93
    </h6>
    1.99
    </h5>
    1.72
    </h4>
    1.54
    </td>
    1.41
    </h1>
    1.40
    </h2>
    1.37
    <h4>
    1.26
    ';
    
    1.26
    </blockquote>
    1.23
    Activations Density 0.056%

    No Known Activations