© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14876
    Prev
    Next
    INDEX
    Explanations

    references to Thomas and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‍♀️
    -0.75
     McGovern
    -0.75
    nologue
    -0.73
    lieger
    -0.69
    UNICIP
    -0.69
    interopRequire
    -0.68
    aurav
    -0.67
    verley
    -0.66
    IContainer
    -0.65
     Juno
    -0.64
    POSITIVE LOGITS
     Thomas
    1.61
    Thomas
    1.41
     THOMAS
    1.30
    THOMAS
    1.26
     thomas
    1.22
     Tomas
    1.17
    thomas
    1.14
     Thom
    1.06
    Tomas
    1.05
     Tomás
    1.05
    Activations Density 0.009%

    No Known Activations