© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12633
    Prev
    Next
    INDEX
    Explanations

    structured data formats, particularly those involving lists and dictionaries

    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
     itſelf
    -0.81
     pleaſure
    -0.80
     myſelf
    -0.79
     whoſe
    -0.77
     themſelves
    -0.76
     faſt
    -0.75
     noDo
    -0.73
     Theſe
    -0.70
     himſelf
    -0.69
     becauſe
    -0.69
    POSITIVE LOGITS
    },[
    0.48
    spli
    0.48
    </table>
    0.48
    awtextra
    0.46
     Pelham
    0.45
    engk
    0.44
    Hozzáférés
    0.44
     proceeding
    0.44
    comune
    0.44
    டம்
    0.44
    Activations Density 0.463%

    No Known Activations