© 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. 20-GEMMASCOPE-RES-16K
    11. 8351
    Prev
    Next
    INDEX
    Explanations

    mentions of significant market factors or trends

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

    Follows "the" or "." in English text

    np_acts-logits-general · gemini-2.0-flash

    the followed by adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decidedly
    -0.66
     admittedly
    -0.59
    bajo
    -0.54
    presumably
    -0.50
    WithMany
    -0.50
     ostensibly
    -0.50
     désormais
    -0.47
    essentially
    -0.47
    Toponymie
    -0.47
     Somewhat
    -0.47
    POSITIVE LOGITS
     said
    0.82
    mergeFrom
    0.74
     equipments
    0.73
     concerned
    0.70
    ləş
    0.70
     mentioned
    0.69
    styleType
    0.69
    AutoScale
    0.68
     aforesaid
    0.68
     OFDb
    0.68
    Activations Density 0.971%

    No Known Activations