Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5865
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize ongoing actions or conditions

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

    the word "while" in various contexts.

    oai_token-act-pair · gpt-4oTriggered by @christianthto

    "while" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    while followed by ongoing activity

    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
    ніципалі
    -0.60
     /\.
    -0.57
    them
    -0.51
    Geografi
    -0.51
    msgid
    -0.48
    */
    -0.47
    rds
    -0.44
    će
    -0.43
    Linki
    -0.43
    xxx
    -0.43
    POSITIVE LOGITS
     they
    1.11
     still
    1.01
     simultaneously
    0.97
     others
    0.97
     we
    0.95
    still
    0.92
     awaiting
    0.87
    others
    0.80
     OTHERS
    0.78
     nahilalakip
    0.76
    Activations Density 0.081%

    No Known Activations