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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1150
    Prev
    Next
    INDEX
    Explanations

    code related to fetching data, particularly successful responses from an action in a programming context

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

    Follows "<start_of_turn>user"

    np_acts-logits-general · gemini-2.0-flash

    user input context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.39
    enterOuterAlt
    -0.37
     zad
    -0.31
    ?>
    
    -0.30
     ویکی‌پدی
    -0.29
     einzu
    -0.29
    ">//
    -0.29
    |}{\
    -0.29
    springframework
    -0.28
    odly
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.87
    SequentialGroup
    0.75
    ⤹
    0.65
    aarrggbb
    0.59
    
    0.57
    psack
    0.53
     disambiguazione
    0.53
    nhung
    0.52
    뀔
    0.52
    cinct
    0.50
    Activations Density 0.062%

    No Known Activations