© 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-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12655
    Prev
    Next
    INDEX
    Explanations

    identifiers and variable names in code

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

    Characters, symbols, and punctuation

    np_acts-logits-general · gemini-2.0-flash

    code snippets, mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.94
     kaarangay
    -0.91
     ſind
    -0.84
    ðsíða
    -0.82
    ésultats
    -0.79
     الحره
    -0.79
    majánló
    -0.79
     queſta
    -0.79
    niſſe
    -0.78
     zijne
    -0.78
    POSITIVE LOGITS
     +
    0.46
    ,
    0.46
    ↵↵
    0.45
    /
    0.41
     itself
    0.40
    less
    0.40
    -
    0.40
    <strong>
    0.40
    <eos>
    0.40
    ↵
    0.39
    Activations Density 1.383%

    No Known Activations