© 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. 22-GEMMASCOPE-RES-16K
    11. 2969
    Prev
    Next
    INDEX
    Explanations

    symbolic representations, particularly punctuations and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URL query parameters

    np_acts-logits-general · gemini-2.0-flash

    URL query parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.56
    expandindo
    -0.55
    ñana
    -0.53
    ✨:
    -0.51
    Kjelder
    -0.48
    GARET
    -0.47
     Jank
    -0.47
     par
    -0.47
     saites
    -0.46
    ELINES
    -0.46
    POSITIVE LOGITS
    TagMode
    0.75
    utm
    0.71
    amp
    0.69
    LEncoder
    0.67
    q
    0.67
    type
    0.64
    IsContent
    0.63
    ecap
    0.61
    _=
    0.61
    mode
    0.61
    Activations Density 0.169%

    No Known Activations