© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9502
    Prev
    Next
    INDEX
    Explanations

    technical and programming-related terms, particularly concerning file paths and code structures

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

    File paths

    np_acts-logits-general · gemini-2.0-flash

    file paths and web links

    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
    ?,?,
    -0.58
    />,
    -0.54
    **,
    -0.53
    ":"",
    -0.50
     سكانية
    -0.48
     farlo
    -0.48
    السكان
    -0.48
    %?
    -0.47
    ::__
    -0.46
    ,–
    -0.46
    POSITIVE LOGITS
    <unused63>
    0.73
     يتيمه
    0.71
    <unused60>
    0.68
    <unused61>
    0.67
    <unused62>
    0.66
    fjspx
    0.65
    AnchorStyles
    0.59
    uminense
    0.58
    Bronnen
    0.58
     EconPapers
    0.58
    Activations Density 0.265%

    No Known Activations