© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 78124
    Prev
    Next
    INDEX
    Explanations

    expressions related to urgency and time constraints

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

    states of completion or being

    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
     (@
    -0.42
    (@
    -0.30
    @
    -0.28
     whose
    -0.27
     course
    -0.26
     apparently
    -0.25
    ianus
    -0.25
    (`
    -0.24
    /
    -0.24
     @
    -0.24
    POSITIVE LOGITS
    MLLoader
    0.89
    setVerticalGroup
    0.83
    contentLoaded
    0.81
     EconPapers
    0.79
    DIPSETTING
    0.79
    <unused41>
    0.78
    <unused52>
    0.77
    <unused79>
    0.77
    <unused28>
    0.77
    <unused23>
    0.77
    Activations Density 0.054%

    No Known Activations