© 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. 16-GEMMASCOPE-RES-16K
    11. 1740
    Prev
    Next
    INDEX
    Explanations

    affirmative language that indicates certainty or emphasis

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

    Follows "definitely" or "clearly"

    np_acts-logits-general · gemini-2.0-flash

    emphasizing a characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simplesmente
    -0.60
     Lass
    -0.52
    Essentially
    -0.52
     essentially
    -0.51
    ess
    -0.51
     Essentially
    -0.50
    how
    -0.50
    bard
    -0.49
    Bare
    -0.49
    How
    -0.48
    POSITIVE LOGITS
    انيف
    0.85
     فريبيس
    0.85
    ConstraintMaker
    0.83
    Tikang
    0.82
    GEBURTSDATUM
    0.82
    !!</
    0.80
    PhysRevD
    0.79
     <=",
    0.78
    IVEREF
    0.78
     Signalez
    0.78
    Activations Density 0.102%

    No Known Activations