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. 16-GEMMASCOPE-RES-16K
    6. 1416
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structuring in equations

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

    Commas not followed by spaces

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.90
     ExecuteAsync
    -0.86
    providedIn
    -0.82
    InputBorder
    -0.68
    Tembelea
    -0.67
    endphp
    -0.66
    Nuorodos
    -0.66
     препратки
    -0.65
    Šaltiniai
    -0.65
    iastes
    -0.65
    POSITIVE LOGITS
     kasarigan
    0.52
     nhàng
    0.49
    SerializeField
    0.48
    enggarakan
    0.48
    unschweig
    0.47
    iteness
    0.45
     disponibilités
    0.45
    arcoma
    0.45
    berkeley
    0.44
    следова
    0.44
    Activations Density 0.697%

    No Known Activations