© 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. 4-GEMMASCOPE-RES-16K
    6. 12838
    Prev
    Next
    INDEX
    Explanations

    references to youth organizations and community involvement activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scale
    -0.90
     scales
    -0.82
     scaled
    -0.79
     scaling
    -0.75
    scale
    -0.72
    Atsauces
    -0.71
    ValueGeneration
    -0.70
     Scale
    -0.69
    scaled
    -0.67
    ніципалі
    -0.67
    POSITIVE LOGITS
     volunteer
    0.80
     vrijwilli
    0.74
     volunteers
    0.73
     Volunteer
    0.73
     voluntarios
    0.72
    Volunteer
    0.72
     bénévoles
    0.71
     volunteering
    0.70
     hobby
    0.70
     Scouts
    0.69
    Activations Density 0.383%

    No Known Activations