© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5942
    Prev
    Next
    INDEX
    Explanations

    references to specific models of sneakers and their releases

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

    "Nike" or "<start_of_turn> user"

    np_acts-logits-general · gemini-2.0-flash

    Nike and supra shoe brands

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     zufolge
    -0.32
     fis
    -0.30
     competente
    -0.27
     szerint
    -0.25
     pudieran
    -0.25
    %;">
    -0.24
     autorytatywna
    -0.24
     Thorne
    -0.23
    نامه
    -0.23
     distributed
    -0.23
    POSITIVE LOGITS
    istoitu
    0.70
    aarrggbb
    0.69
    twimg
    0.60
    хьтан
    0.60
    WebServlet
    0.59
    évaluateur
    0.56
    جوايز
    0.55
    ConstraintMaker
    0.53
     transfieras
    0.53
    Nike
    0.53
    Activations Density 0.076%

    No Known Activations