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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 11157
    Prev
    Next
    INDEX
    Explanations

    references to scenes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ostante
    -0.74
     useDispatch
    -0.70
     đảo
    -0.68
     egyszer
    -0.66
     cortas
    -0.66
    PerformLayout
    -0.66
    onChanged
    -0.66
    hematical
    -0.62
    AndEndTag
    -0.61
     philosophie
    -0.61
    POSITIVE LOGITS
     scene
    3.67
     Scene
    3.32
     scenes
    3.30
     SCENE
    3.16
    scene
    3.10
    Scene
    2.95
     Scenes
    2.87
    SCENE
    2.62
    scenes
    2.54
    Scenes
    2.40
    Activations Density 0.036%

    No Known Activations