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. 9-GEMMASCOPE-RES-16K
    6. 1566
    Prev
    Next
    INDEX
    Explanations

    references to specific scenes or scene structures in a narrative or script

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    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
    -0.81
    hematical
    -0.77
    hitung
    -0.75
    multer
    -0.75
     fortsatt
    -0.71
    üyük
    -0.71
     cortas
    -0.70
    RetentionPolicy
    -0.70
     egyszer
    -0.69
    rália
    -0.65
    POSITIVE LOGITS
     scene
    2.15
     SCENE
    2.02
     scenes
    2.01
     Scene
    2.00
    scene
    1.76
     Scenes
    1.74
    SceneManagement
    1.72
    Scene
    1.72
    SCENE
    1.62
    Scenes
    1.52
    Activations Density 0.036%

    No Known Activations