© 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. 14700
    Prev
    Next
    INDEX
    Explanations

    references to types of media and their classifications

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

    Follows "type" or "and", then a description

    np_acts-logits-general · gemini-2.0-flash

    type and subtype

    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
    ègre
    -0.61
    Виды
    -0.60
     unterschiedlich
    -0.58
     différente
    -0.58
     المختلفة
    -0.54
     verschieden
    -0.52
    Different
    -0.52
    anele
    -0.50
     variétés
    -0.50
     Revisited
    -0.50
    POSITIVE LOGITS
     ModelExpression
    0.74
     protoimpl
    0.65
    stylers
    0.61
     }^{*
    0.60
    PMailer
    0.56
    Hozzáférés
    0.55
    WriteBarrier
    0.55
    Viitteet
    0.54
    AutoresizingMask
    0.54
     lenker
    0.52
    Activations Density 0.485%

    No Known Activations