© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 65240
    Prev
    Next
    INDEX
    Explanations

    references to LaTeX packages related to mathematical typesetting and graphics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    enumi
    -0.59
    SequentialGroup
    -0.52
    GeneratedValue
    -0.49
    󠁢
    -0.47
     Normdatei
    -0.45
     Chwiliwch
    -0.44
    AutoField
    -0.44
     незавершена
    -0.43
     &___
    -0.43
    inheritDoc
    -0.42
    POSITIVE LOGITS
    ThemeOverlay
    0.53
    amsmath
    0.51
    Rhestr
    0.48
    <bos>
    0.44
    zeptember
    0.41
    المكان
    0.40
     verſ
    0.40
     geſ
    0.40
    AddHtmlAttribute
    0.40
    gü
    0.39
    Activations Density 0.000%

    No Known Activations