Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13978
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics, particularly focused on rushing and passing yards in football

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getConfig
    -0.48
    Conf
    -0.47
     Conf
    -0.44
    uteria
    -0.44
     theo
    -0.44
     Barton
    -0.44
     klaus
    -0.43
    onnes
    -0.42
     neum
    -0.42
    hability
    -0.42
    POSITIVE LOGITS
    runApp
    0.77
     gql
    0.73
     MonoBehaviour
    0.69
     thighs
    0.67
    ChildScrollView
    0.65
     sprints
    0.64
    ---*/
    0.64
     bodyParser
    0.64
    IntoConstraints
    0.64
     XCTest
    0.64
    Activations Density 0.115%

    No Known Activations