© 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. 18-GEMMASCOPE-RES-16K
    11. 8926
    Prev
    Next
    INDEX
    Explanations

    descriptions of locations and amenities

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

    Follows punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.68
    ITERATURE
    -0.67
     goddamn
    -0.67
     Theſe
    -0.67
    apimachinery
    -0.67
     NDEBUG
    -0.66
    ">${
    -0.65
     Apparently
    -0.63
     Efq
    -0.62
    >`;
    -0.62
    POSITIVE LOGITS
     spacious
    0.68
    !
    0.64
     oportunidade
    0.62
     beautifully
    0.61
     immaculate
    0.59
    prepareStatement
    0.58
    !!
    0.58
     perfect
    0.58
     Located
    0.56
     located
    0.56
    Activations Density 0.047%

    No Known Activations