© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3635
    Prev
    Next
    INDEX
    Explanations

    terms related to urgency or immediate action

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

    following "immediate"

    np_acts-logits-general · gemini-2.0-flash

    immediate events or descriptors

    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
    nemia
    -0.52
     estekak
    -0.52
     fout
    -0.50
     opérateur
    -0.48
     ExecuteAsync
    -0.47
     strijd
    -0.47
    結果は
    -0.47
     BeautifulSoup
    -0.46
     handleChange
    -0.46
     getLayout
    -0.46
    POSITIVE LOGITS
     moment
    0.85
    moment
    0.82
    Moment
    0.76
     Moment
    0.71
     MOMENT
    0.70
     instant
    0.63
     immedi
    0.61
     momento
    0.60
     Instant
    0.60
    Immediate
    0.58
    Activations Density 0.263%

    No Known Activations