© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 669
    Prev
    Next
    INDEX
    Explanations

    event handling and function definitions in JavaScript code

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

    prevention or obstruction

    np_acts-logits-general · gemini-2.0-flash

    stop propagation or prevention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ChildScrollView
    -0.59
    FieldBuilder
    -0.58
    RectangleBorder
    -0.58
    ConstraintMaker
    -0.55
    ParallelGroup
    -0.55
    WithMany
    -0.51
     חיצוניים
    -0.49
    LLocation
    -0.48
    onAttach
    -0.48
    RuleContext
    -0.48
    POSITIVE LOGITS
    preventDefault
    0.54
     prevented
    0.48
    Prevent
    0.45
     preventing
    0.45
     empêcher
    0.44
     prevent
    0.44
     Prevent
    0.44
     arrest
    0.41
    stopPropagation
    0.40
     prevention
    0.40
    Activations Density 0.101%

    No Known Activations