© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7523
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a sense of something being previously done or established

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

    "Already" followed by a past participle

    np_acts-logits-general · gemini-2.0-flash

    already known or done

    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
    still
    -1.16
     still
    -1.10
     todavía
    -1.00
     aún
    -0.99
    Still
    -0.97
     ancora
    -0.96
     Still
    -0.96
     ainda
    -0.96
     fortfarande
    -0.94
     also
    -0.91
    POSITIVE LOGITS
     begun
    0.82
     established
    0.77
     BoxFit
    0.73
    IsMutable
    0.70
    tellen
    0.68
     onCreateView
    0.68
    دانشنامهٔ
    0.68
     know
    0.67
    findpost
    0.66
    tehen
    0.65
    Activations Density 0.074%

    No Known Activations