© 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. 8187
    Prev
    Next
    INDEX
    Explanations

    medical guidelines and warnings

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

    Follows bullet points, colons, periods, and warnings

    np_acts-logits-general · gemini-2.0-flash

    warnings and safety information

    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
     justement
    -0.52
     Interestingly
    -0.51
     tweaked
    -0.50
     pretty
    -0.50
    anskje
    -0.50
     Eso
    -0.49
    ValueStyle
    -0.49
    Interestingly
    -0.49
     bugged
    -0.48
     hopefully
    -0.47
    POSITIVE LOGITS
     nigdy
    0.69
     الرياضيه
    0.68
    Never
    0.66
    CAUTION
    0.66
     prosím
    0.63
    Consult
    0.63
     CAUTION
    0.63
     WARNING
    0.63
    ſelf
    0.62
     niemals
    0.61
    Activations Density 0.192%

    No Known Activations