© 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. 11405
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effectiveness or impact of certain factors or interventions

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

    smallness or lack of impact

    np_acts-logits-general · gemini-2.0-flash

    little quantity

    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
     ivelany
    -0.60
     Wiktionnaire
    -0.49
    reactstrap
    -0.48
    ίος
    -0.44
    WritableDatabase
    -0.44
    aarrggbb
    -0.44
    inya
    -0.44
    temming
    -0.44
    Története
    -0.43
    inghouse
    -0.43
    POSITIVE LOGITS
     little
    2.45
    little
    2.09
     minimal
    1.87
     weinig
    1.77
     hardly
    1.74
     wenig
    1.73
     LITTLE
    1.73
     peu
    1.70
     fewer
    1.69
     less
    1.67
    Activations Density 1.116%

    No Known Activations