© 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. 20-GEMMASCOPE-RES-16K
    11. 11922
    Prev
    Next
    INDEX
    Explanations

    strings of numerical codes or specific formatting patterns 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 @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.79
    GEBURTSDATUM
    -0.55
    :✨
    -0.53
    richTextPanel
    -0.53
    GetAxis
    -0.53
     تانيه
    -0.52
    PreExecute
    -0.52
    RenderAtEndOf
    -0.52
    esez
    -0.51
    rophe
    -0.50
    POSITIVE LOGITS
    __(/*!
    0.62
     instantly
    0.58
    __":
    0.58
     suddenly
    0.58
     seemed
    0.57
    AccessException
    0.57
     COVERAGE
    0.56
     ['./
    0.53
     silhouettes
    0.53
    곳
    0.52
    Activations Density 0.057%

    No Known Activations