© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 9532
    Prev
    Next
    INDEX
    Explanations

    elements related to code syntax and structure

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

    quoting or citing text

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    oa̍t
    -0.62
    хьтан
    -0.61
    Personensuche
    -0.58
    Rujuakan
    -0.57
     gynhyrchwyd
    -0.55
     Numerade
    -0.55
     unknownFields
    -0.53
    #+#
    -0.51
    IndentedString
    -0.50
     jsPsych
    -0.50
    POSITIVE LOGITS
    quote
    0.78
    Quote
    0.76
     quote
    0.73
     "...
    0.66
     Quote
    0.59
     excerpt
    0.58
     quoting
    0.57
    Excerpt
    0.57
    QUOTE
    0.56
    Zitat
    0.55
    Activations Density 0.117%

    No Known Activations