© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2236
    Prev
    Next
    INDEX
    Explanations

    occurrences and frequencies of events or actions

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

    "times" or "twice"

    np_acts-logits-general · gemini-2.0-flash

    frequency of events

    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
    regard
    -0.48
     uLocal
    -0.48
    IntoConstraints
    -0.47
    <0x84>
    -0.42
     anuncio
    -0.42
    Jury
    -0.41
    ècie
    -0.39
    RQ
    -0.39
    DOE
    -0.38
    considerable
    -0.37
    POSITIVE LOGITS
     Twice
    0.82
     thrice
    0.81
     twice
    0.80
    Twice
    0.78
     TIMES
    0.76
     times
    0.74
     TWICE
    0.71
    twice
    0.69
     Times
    0.68
    又一次
    0.68
    Activations Density 0.145%

    No Known Activations