© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1156
    Prev
    Next
    INDEX
    Explanations

    information related to television programming and casting changes

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

    able to

    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
     hashtag
    -0.92
     hash
    -0.88
     hashtags
    -0.85
     Hash
    -0.82
     Hashtag
    -0.77
    Hash
    -0.71
     tag
    -0.70
     tags
    -0.69
    hashtag
    -0.66
     Tag
    -0.66
    POSITIVE LOGITS
    ValueStyle
    0.54
     ExecuteAsync
    0.42
    rzost
    0.40
    出版年
    0.39
    localctx
    0.38
    Seeder
    0.36
    protoimpl
    0.35
     snippetHide
    0.35
    DataBind
    0.34
     Blake
    0.34
    Activations Density 0.020%

    No Known Activations