Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 65473
    Prev
    Next
    INDEX
    Explanations

    references to international standards and regulations, particularly those related to ISO

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

    standards and formats

    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
    GTCX
    -0.58
    BufferException
    -0.57
    الإنجليزية
    -0.56
     SwitchCompat
    -0.56
    idencial
    -0.54
     OFDb
    -0.54
     Obrador
    -0.53
    Tracklist
    -0.52
     unknownFields
    -0.52
    complexContent
    -0.50
    POSITIVE LOGITS
     ब्रेकडाउन
    0.49
     ISO
    0.42
     globalization
    0.39
    ISO
    0.34
     disambiguazione
    0.33
     Globalization
    0.33
     palsu
    0.29
    beforeAll
    0.29
    giène
    0.28
    asanjo
    0.28
    Activations Density 0.005%

    No Known Activations