© 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. 3725
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or data points within a text

    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
     urbaine
    -0.59
     médicaux
    -0.58
    qrstuvwxyz
    -0.58
    kusen
    -0.55
    atschappij
    -0.55
    ISupport
    -0.55
    COMMENTS
    -0.53
    UserScript
    -0.53
    seamnă
    -0.53
    väg
    -0.52
    POSITIVE LOGITS
    (
    0.58
    <$
    0.57
    RectangleBorder
    0.57
    DoubleQuotes
    0.57
    (>
    0.56
    Autoritní
    0.56
    }(),
    0.56
    İstinadlar
    0.52
     Drapeau
    0.52
    ($
    0.51
    Activations Density 0.202%

    No Known Activations