© 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. 4-GEMMASCOPE-RES-16K
    6. 9904
    Prev
    Next
    INDEX
    Explanations

    mentions of specific scenes or scene numbers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     egyszer
    -0.80
    ostante
    -0.79
     cortas
    -0.69
     sorella
    -0.67
     jspb
    -0.67
     سكانية
    -0.66
    AndEndTag
    -0.66
    hematical
    -0.66
     mathématiques
    -0.65
    üyük
    -0.64
    POSITIVE LOGITS
     scene
    3.13
     scenes
    2.93
     Scene
    2.83
     SCENE
    2.71
    scene
    2.65
    Scene
    2.52
     Scenes
    2.51
    SCENE
    2.25
    scenes
    2.23
     scènes
    2.16
    Activations Density 0.044%

    No Known Activations