© 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. 17-GEMMASCOPE-RES-16K
    6. 1959
    Prev
    Next
    INDEX
    Explanations

    athletic achievements and performance metrics in sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referències
    -0.45
    "?>
    -0.43
    ustand
    -0.42
    orianCalendar
    -0.41
    eton
    -0.40
     swollen
    -0.40
    Gerd
    -0.40
     policiers
    -0.40
     BaseController
    -0.40
    conv
    -0.39
    POSITIVE LOGITS
     teams
    1.75
     team
    1.64
    Teams
    1.56
     Teams
    1.55
     Team
    1.46
    Team
    1.45
    teams
    1.44
    team
    1.38
    TEAM
    1.29
     TEAM
    1.29
    Activations Density 0.137%

    No Known Activations