© 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. 11-GEMMASCOPE-RES-16K
    11. 13431
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting indicators in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lo
    -0.60
    ))/(
    -0.59
     cap
    -0.54
    )"),
    -0.54
    zwi
    -0.54
     سكان
    -0.51
     getIs
    -0.50
    %"),
    -0.49
    )){
    -0.49
    thâu
    -0.48
    POSITIVE LOGITS
    +#+
    0.77
     يتيمه
    0.76
     utafitiHapana
    0.73
    ########.
    0.72
     purpoſe
    0.71
    adaptiveStyles
    0.69
     houſe
    0.68
     Majefty
    0.67
    ConstraintMaker
    0.67
    ſelf
    0.66
    Activations Density 0.303%

    No Known Activations