© 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 - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 2902
    Prev
    Next
    INDEX
    Explanations

    references to films and filmmaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wendell
    -0.74
    ANTAGE
    -0.74
    zura
    -0.74
     Rache
    -0.70
    संद
    -0.69
     trône
    -0.69
     COU
    -0.69
    wies
    -0.69
     Huck
    -0.68
     repres
    -0.67
    POSITIVE LOGITS
     FILM
    1.33
     films
    1.28
     Film
    1.24
     film
    1.21
     Films
    1.19
     invokingState
    1.18
     FILMS
    1.17
    Films
    1.17
    films
    1.14
    Film
    1.12
    Activations Density 0.057%

    No Known Activations