© 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. 35-GEMMASCOPE-RES-16K
    11. 9125
    Prev
    Next
    INDEX
    Explanations

    code diff markers and signs of code modification in version control systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.75
    ValueStyle
    -0.73
     հղումներ
    -0.71
    ConstraintMaker
    -0.70
    astify
    -0.69
    WriteTagHelper
    -0.67
    ValueGeneration
    -0.65
    الحياه
    -0.64
    TextSpan
    -0.64
    лтамалар
    -0.63
    POSITIVE LOGITS
     simplifié
    0.31
     corporation
    0.30
     postings
    0.29
    ◜
    0.29
     boundary
    0.29
     domino
    0.29
     manifest
    0.28
     posting
    0.28
     execution
    0.28
     high
    0.28
    Activations Density 0.148%

    No Known Activations