© 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. 3569
    Prev
    Next
    INDEX
    Explanations

    code-related comments and annotations

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

    Code comments and auto-generated code

    np_acts-logits-general · gemini-2.0-flash

    code structures

    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
    userdetails
    -0.56
    enumii
    -0.50
     faudrait
    -0.48
     among
    -0.47
    Архівовано
    -0.47
     fallait
    -0.47
     ${({
    -0.46
    riwal
    -0.46
    Royce
    -0.46
    enumi
    -0.45
    POSITIVE LOGITS
    BagConstraints
    0.67
    ."));
    0.67
     resourceCulture
    0.66
    تقاوى
    0.65
    findpost
    0.64
    Datuak
    0.61
     jspb
    0.61
     चीज़ों
    0.58
    verifyException
    0.57
     CHtml
    0.57
    Activations Density 0.120%

    No Known Activations