© 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. 8222
    Prev
    Next
    INDEX
    Explanations

    metadata related to document authorship and copyright information

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

    Code comments, headers, and licenses

    np_acts-logits-general · gemini-2.0-flash

    code comments and author names

    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
    下载附件
    -0.65
     himſelf
    -0.62
     itſelf
    -0.60
    RenderAtEndOf
    -0.58
    SequentialGroup
    -0.54
     ſch
    -0.52
     themſelves
    -0.51
    ſelves
    -0.49
     ſche
    -0.49
     boneca
    -0.48
    POSITIVE LOGITS
    GOTREF
    0.49
     HasFactory
    0.46
     Be
    0.41
     Cortez
    0.40
     Architect
    0.39
    .*")]
    0.39
     koc
    0.39
     Season
    0.39
     fark
    0.38
     Race
    0.37
    Activations Density 0.097%

    No Known Activations