© 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. 12228
    Prev
    Next
    INDEX
    Explanations

    articles, both definite and indefinite, in the text

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

    articles followed by nouns/adjectives

    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
    Попис
    -0.52
     nemlig
    -0.50
     iaitu
    -0.45
     étoit
    -0.41
     feroit
    -0.40
    seamnă
    -0.36
     yaitu
    -0.36
     auroit
    -0.35
     pouvoit
    -0.34
     namelijk
    -0.33
    POSITIVE LOGITS
    uxxxx
    0.64
     defaultstate
    0.63
     lastly
    0.57
    その他
    0.57
    めでとう
    0.56
    الحياه
    0.56
    RTHOOK
    0.55
     etc
    0.55
     downright
    0.54
     subsequent
    0.53
    Activations Density 0.083%

    No Known Activations