© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6047
    Prev
    Next
    INDEX
    Explanations

    probabilities or statistics related to health metrics and conditions

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

    Numbers inside parentheses

    np_acts-logits-general · gemini-2.0-flash

    percentages and numbers

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     record
    -0.41
    enderror
    -0.39
     Yaz
    -0.36
     attorney
    -0.35
    DispatchToProps
    -0.35
     ger
    -0.35
     bishop
    -0.35
     ändå
    -0.34
    perger
    -0.34
     remote
    -0.34
    POSITIVE LOGITS
    ConstraintMaker
    0.75
    transQ
    0.67
    ArrowToggle
    0.65
    ScopeManager
    0.64
    IVEREF
    0.63
     հղումներ
    0.62
     noDo
    0.61
    MessageOf
    0.59
     protoimpl
    0.58
    RTSC
    0.57
    Activations Density 1.660%

    No Known Activations