© 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. 8193
    Prev
    Next
    INDEX
    Explanations

    words or characters that are part of transcriptions or phonetics

    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
    Pyx
    -0.70
    :✨
    -0.69
    rrh
    -0.66
    Gweler
    -0.63
    таратура
    -0.61
    ništ
    -0.58
    хь
    -0.57
    ільки
    -0.57
    Бахар
    -0.56
     nahilalakip
    -0.56
    POSITIVE LOGITS
    usercontent
    0.56
    ISupport
    0.49
    amerika
    0.48
     typelib
    0.47
     रेटिंग
    0.46
    mapStateToProps
    0.43
    setopt
    0.38
     managing
    0.38
    managing
    0.38
    KEYCODE
    0.38
    Activations Density 0.015%

    No Known Activations