© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8847
    Prev
    Next
    INDEX
    Explanations

    proper names of people or entities

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

    proper nouns and names, particularly surnames and scientific/technical nomenclature.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nya
    -0.69
    ness
    -0.65
    ם
    -0.62
    ن
    -0.57
    tagHelperRunner
    -0.56
    น
    -0.56
    نا
    -0.54
    nat
    -0.54
    natural
    -0.49
    nagar
    -0.49
    POSITIVE LOGITS
    iiii
    0.58
    ی
    0.54
    깐
    0.54
    iiiiiiii
    0.53
    iiiii
    0.52
    hdi
    0.50
    Di
    0.50
    rici
    0.50
    ppi
    0.50
    postIndex
    0.49
    Activations Density 0.661%

    No Known Activations