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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1352
    Prev
    Next
    INDEX
    Explanations

    probability-related terms in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendriers
    -0.77
     lenker
    -0.72
    ValueGeneration
    -0.72
     transfieras
    -0.66
    WEBPACK
    -0.66
    __(/*!
    -0.65
    WireFormat
    -0.64
    InjectAttribute
    -0.61
     nahilalakip
    -0.60
    SuppressMessage
    -0.58
    POSITIVE LOGITS
    o
    0.77
    l
    0.76
    r
    0.74
    m
    0.74
    S
    0.73
    s
    0.72
    w
    0.72
    p
    0.71
    t
    0.71
    h
    0.70
    Activations Density 1.902%

    No Known Activations