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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2777
    Prev
    Next
    INDEX
    Explanations

    terms related to sports techniques and statistics, particularly in baseball and martial arts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     sleep
    -0.48
    ews
    -0.46
     cascada
    -0.44
    bena
    -0.43
    ruhe
    -0.43
    المشاركات
    -0.43
    tség
    -0.43
    oureux
    -0.43
     Neri
    -0.42
     بست
    -0.42
    POSITIVE LOGITS
    Portale
    0.83
    MigrationBuilder
    0.83
     MessageBoxIcon
    0.83
     виправивши
    0.80
     дописавши
    0.79
    DockStyle
    0.77
    AnimationsModule
    0.73
     оригіналу
    0.71
     CURIAM
    0.69
     gynhyrchwyd
    0.67
    Activations Density 0.224%

    No Known Activations