Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12659
    Prev
    Next
    INDEX
    Explanations

    functionality and properties related to node management and parameter handling in code

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

    Punctuation, brackets, or symbols

    np_acts-logits-general · gemini-2.0-flash

    punctuation and short words

    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
    </blockquote>
    -1.40
    .’”
    -1.36
    ).”
    -1.31
    )”
    -1.21
    .’
    -1.18
    .”
    -1.17
    .'”
    -1.08
    .”)
    -1.06
    )»
    -1.05
    .’’
    -1.02
    POSITIVE LOGITS
    ",
    2.50
    ',
    2.21
     ",
    1.97
    `,
    1.80
    ?",
    1.69
    .",
    1.68
    ”,
    1.66
    !",
    1.66
    )",
    1.56
     ',
    1.55
    Activations Density 1.074%

    No Known Activations