© 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. 440
    Prev
    Next
    INDEX
    Explanations

    terms related to biological classifications and analytical methods in scientific contexts

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

    technical and scientific terminology, particularly multi-syllabic words that are partially tokenized or appear in formal academic or computational contexts.

    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
    ième
    -1.02
    ised
    -0.97
    ۰
    -0.75
    sweise
    -0.72
    ians
    -0.72
    ação
    -0.72
    ový
    -0.72
    StateToProps
    -0.69
    ología
    -0.68
    ۰۰
    -0.68
    POSITIVE LOGITS
    <bos>
    0.82
    してみて
    0.58
    cob
    0.57
    pop
    0.56
    cot
    0.56
    peg
    0.56
    pod
    0.54
    pak
    0.54
    bee
    0.54
    uni
    0.53
    Activations Density 4.141%

    No Known Activations