© 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 EvalsExportsAPI 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. 44267
    Prev
    Next
    INDEX
    Explanations

    identifiers and names related to objects and elements in a code or programming context, with a specific focus on candy apples as a cultural reference

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

    HTML attribute names

    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
     informée
    -0.86
     utafitiHapana
    -0.79
    tanleria
    -0.70
     GenerationType
    -0.69
     queſta
    -0.66
     ſind
    -0.65
     enfans
    -0.62
    Дереккөздер
    -0.61
    ckså
    -0.61
    KommentareTeilen
    -0.61
    POSITIVE LOGITS
    零
    0.33
     sk
    0.33
     пора
    0.31
    ///</
    0.30
     bu
    0.29
    ingen
    0.29
    localctx
    0.28
    RTLI
    0.28
     朱
    0.28
     remot
    0.28
    Activations Density 0.350%

    No Known Activations