© 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. 9-GEMMASCOPE-RES-131K
    6. 34791
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical values and identifiers

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

    court, jurisdiction, or legal documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RequestMethod
    -0.44
     affitto
    -0.40
    awaiter
    -0.40
     comunicazione
    -0.38
    loro
    -0.38
    ագ
    -0.37
    ulz
    -0.37
     Bun
    -0.37
     c
    -0.37
    humanité
    -0.36
    POSITIVE LOGITS
    transQ
    0.60
     للمعارف
    0.59
     الرياضيه
    0.51
     ligiloj
    0.50
     utafitiHapana
    0.47
     nahilalakip
    0.47
    Portail
    0.47
    Referanser
    0.45
    Географиясе
    0.43
    Portale
    0.42
    Activations Density 0.062%

    No Known Activations