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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1144
    Prev
    Next
    INDEX
    Explanations

    assignment operations and conditional statements

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

    else and otherwise in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.74
    LookAnd
    -0.63
     للمعارف
    -0.55
    évaluateur
    -0.50
    AccessorTable
    -0.48
     ब्रेकडाउन
    -0.48
     Numerade
    -0.47
    erom
    -0.46
    MigrationBuilder
    -0.45
    InstrumentedTest
    -0.44
    POSITIVE LOGITS
     الحره
    0.43
     otherwise
    0.42
    enumii
    0.41
     juist
    0.38
    AnchorStyles
    0.38
     chi̍t
    0.36
     else
    0.36
     NUKAT
    0.35
     just
    0.34
     raczej
    0.34
    Activations Density 0.016%

    No Known Activations