© 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. 7526
    Prev
    Next
    INDEX
    Explanations

    words that indicate re-evaluation or reconsideration processes

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

    starting with "re" followed by a hyphen

    np_acts-logits-general · gemini-2.0-flash

    re- followed by common stems

    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
     définiti
    -0.71
    inerja
    -0.69
    bootstrapcdn
    -0.66
     olvidado
    -0.66
     cappello
    -0.65
     Wandel
    -0.65
    attendre
    -0.65
     préfé
    -0.64
    providedIn
    -0.63
     disponibilités
    -0.62
    POSITIVE LOGITS
    AccessFile
    0.55
     re
    0.52
    energ
    0.48
    StoryboardSegue
    0.46
     inst
    0.46
    prior
    0.46
    olastic
    0.45
    wright
    0.45
     rem
    0.45
    jig
    0.45
    Activations Density 0.116%

    No Known Activations