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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 2782
    Prev
    Next
    INDEX
    Explanations

    words related to freshness or newness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.81
    bootstrapcdn
    -0.76
    thâu
    -0.73
    AndroidJUnit
    -0.71
     متعلقه
    -0.67
     ModelExpression
    -0.64
    WithIOException
    -0.62
    PreferredItem
    -0.61
     >=",
    -0.59
     EventEmitter
    -0.58
    POSITIVE LOGITS
     FRESH
    1.13
     fresh
    1.12
     Fresh
    1.11
    Fresh
    1.08
    fresh
    1.05
    FRESH
    0.95
     fresca
    0.95
     frescas
    0.90
     fres
    0.89
     świe
    0.88
    Activations Density 0.028%

    No Known Activations