© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13101
    Prev
    Next
    INDEX
    Explanations

    intensifiers or modifiers that emphasize the degree of an attribute

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

    Follows "very" (or similar adverbs) and modifies an adjective

    np_acts-logits-general · gemini-2.0-flash

    degree adverbs modifying adjectives

    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
    -0.54
     relativement
    -0.48
     terminée
    -0.48
     addirittura
    -0.48
     légèrement
    -0.48
     faisons
    -0.47
     således
    -0.47
     stessa
    -0.46
     nécessairement
    -0.46
     finalement
    -0.45
    POSITIVE LOGITS
    ########.
    0.96
     raiſ
    0.89
    DispatchToProps
    0.88
     Efq
    0.87
     tranſ
    0.83
    ^(@)
    0.83
     nahilalakip
    0.82
     initComponents
    0.81
    RTCK
    0.80
     neceffary
    0.80
    Activations Density 0.237%

    No Known Activations