© 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. 10801
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and self-perception

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

    Possessive pronouns and related words

    np_acts-logits-general · gemini-2.0-flash

    personal interests and choices

    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
    ImageContext
    -0.69
    DoubleQuotes
    -0.62
     שוליים
    -0.62
    oneofs
    -0.57
    ArgumentParser
    -0.55
    netinet
    -0.53
    mstyle
    -0.53
    MathML
    -0.51
    DockStyle
    -0.50
    NameInMap
    -0.50
    POSITIVE LOGITS
     weaknesses
    0.75
     innermost
    0.73
     vulnerabilities
    0.72
    ✨:
    0.71
     own
    0.71
     inner
    0.71
     strengths
    0.70
     personal
    0.69
     surroundings
    0.68
     abilities
    0.68
    Activations Density 0.416%

    No Known Activations