© 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 EvalsExportsinterp-engineNEWAPI 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. 11572
    Prev
    Next
    INDEX
    Explanations

    references to "peak" or "maximum" conditions in various contexts

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

    "peak" or "peaking"

    np_acts-logits-general · gemini-2.0-flash

    highest point

    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
     wireType
    -0.39
     CanadaChoose
    -0.37
     sco
    -0.36
     transférez
    -0.36
    frow
    -0.35
    dibles
    -0.33
    hamshire
    -0.33
    postsleuth
    -0.32
    dams
    -0.32
     balles
    -0.32
    POSITIVE LOGITS
     peak
    1.76
    Peak
    1.56
     Peak
    1.52
    peak
    1.51
     peaks
    1.38
     PEAK
    1.33
     peaked
    1.23
    ピーク
    1.20
     peaking
    1.16
     Peaks
    1.12
    Activations Density 0.465%

    No Known Activations