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. 3-GEMMASCOPE-RES-16K
    6. 12948
    Prev
    Next
    INDEX
    Explanations

    references to zoom levels in descriptions of 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
    Sucesor
    -0.70
    exitRule
    -0.67
    \{\\
    -0.66
    BeginContext
    -0.66
    principalColumn
    -0.63
    లాలు
    -0.63
     propOrder
    -0.62
    カンド
    -0.61
    terase
    -0.60
    expandindo
    -0.60
    POSITIVE LOGITS
     zoom
    3.04
     Zoom
    2.90
    Zoom
    2.86
    zoom
    2.81
     ZOOM
    2.56
    ZOOM
    2.33
     zooming
    2.10
     zoomed
    1.99
     Zo
    1.37
     zo
    1.34
    Activations Density 0.161%

    No Known Activations