© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and positive sentiment towards experiences or objects

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

    Punctuation followed by conjunctions or prepositions

    np_acts-logits-general · gemini-2.0-flash

    especially, or particularly

    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
    そこは
    -0.70
     للاسماء
    -0.61
     Otherwise
    -0.58
    otherwise
    -0.57
    ulets
    -0.57
    prefixer
    -0.56
     indisponible
    -0.55
     Miscellaneous
    -0.55
    Otherwise
    -0.55
     invokingState
    -0.54
    POSITIVE LOGITS
     especially
    1.05
    Especially
    0.99
     Особенно
    0.99
    especially
    0.95
     Especially
    0.90
     even
    0.86
     особенно
    0.85
    собенно
    0.81
     particularly
    0.79
     ESPEC
    0.78
    Activations Density 0.142%

    No Known Activations