Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3874
    Prev
    Next
    INDEX
    Explanations

    references to duality or comparisons involving the word "both."

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

    the word "both"

    np_acts-logits-general · gemini-2.0-flash

    both `NOUN`

    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
    qrstuvwxyz
    -0.70
     nuages
    -0.70
     négociations
    -0.66
     rêves
    -0.66
     spectateurs
    -0.66
    }());
    -0.64
    titleMargin
    -0.63
     dieux
    -0.63
     Chwiliwch
    -0.62
     Grecs
    -0.59
    POSITIVE LOGITS
     sides
    1.08
     versions
    0.79
     halves
    0.78
    sides
    0.75
     parties
    0.75
     ends
    0.75
     sets
    0.71
     side
    0.71
     kinds
    0.68
     of
    0.67
    Activations Density 0.196%

    No Known Activations