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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12908
    Prev
    Next
    INDEX
    Explanations

    statistical data concerning gender demographics and financial behaviors

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

    People reporting or believing something

    np_acts-logits-general · gemini-2.0-flash

    respondents reporting percentages of men and women

    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
    הערות
    -0.63
     AssemblyProduct
    -0.62
    Derbyniad
    -0.60
    ecute
    -0.58
     przecież
    -0.58
    dign
    -0.54
    Ведь
    -0.54
    lemek
    -0.53
    verifyException
    -0.53
    ,:),
    -0.53
    POSITIVE LOGITS
     respondents
    1.41
     surveyed
    1.06
     respondent
    1.05
     Respondents
    0.98
     reported
    0.96
    Respondents
    0.94
     encuesta
    0.92
     polled
    0.85
     survey
    0.85
     responden
    0.79
    Activations Density 1.120%

    No Known Activations