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. 10911
    Prev
    Next
    INDEX
    Explanations

    responses expressing concern or confusion about technical issues or problems

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

    Commas, periods, question marks, and conjunctions

    np_acts-logits-general · gemini-2.0-flash

    discourse markers and transitions

    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
     stipulations
    -0.47
    PhysRevLett
    -0.46
    aughn
    -0.46
    Datuak
    -0.46
    sbericht
    -0.43
    trero
    -0.43
    Essentially
    -0.42
    alace
    -0.42
     box
    -0.42
    baugh
    -0.41
    POSITIVE LOGITS
     Kindly
    0.87
     Anyway
    0.78
    anyway
    0.78
    Moreover
    0.77
     Moreover
    0.76
    Kindly
    0.74
    Actually
    0.74
    Indeed
    0.73
     Indeed
    0.73
    theless
    0.71
    Activations Density 0.256%

    No Known Activations