© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 15168
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "Compton" and references to request options in programming contexts

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

    words ending in pton or ptos

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     RISERVATA
    -0.41
    bufio
    -0.39
     Huse
    -0.38
     Administrativna
    -0.37
    //
    -0.37
     ilang
    -0.36
     Glaser
    -0.36
     Geller
    -0.35
     FBref
    -0.35
    GCC
    -0.35
    POSITIVE LOGITS
    pton
    3.38
    ptons
    1.69
     Krypton
    1.16
     Compton
    1.04
    ptor
    0.89
     Upton
    0.88
    ptos
    0.73
    AMPTON
    0.71
    ption
    0.70
    hampton
    0.68
    Activations Density 0.003%

    No Known Activations