© 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. 50382
    Prev
    Next
    INDEX
    Explanations

    references to lookup operations or functions in programming contexts

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

    performing a lookup

    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
     ThemeData
    -0.47
     Nerv
    -0.47
     endometri
    -0.46
    ButtonModule
    -0.45
    Neutral
    -0.43
    CFLAGS
    -0.42
     setContent
    -0.42
    middlewares
    -0.41
     Neutral
    -0.41
    GenerationType
    -0.41
    POSITIVE LOGITS
    lookup
    2.45
    Lookup
    2.38
     Lookup
    2.27
     lookup
    2.25
    LOOKUP
    2.00
    LookUp
    1.58
     LOOK
    1.34
    look
    1.23
     Look
    1.20
     look
    1.16
    Activations Density 0.003%

    No Known Activations