© 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. 22-GEMMASCOPE-RES-16K
    11. 10845
    Prev
    Next
    INDEX
    Explanations

    references to animals and their interactions

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

    before adverbs or action words

    np_acts-logits-general · gemini-2.0-flash

    running and racing verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -0.92
     Grecs
    -0.83
     auffi
    -0.83
     houſe
    -0.80
     feroit
    -0.78
     endblock
    -0.78
     prêtres
    -0.77
     avoient
    -0.77
     Efq
    -0.76
    setVerticalGroup
    -0.76
    POSITIVE LOGITS
     zi
    0.98
     racing
    0.95
     whi
    0.94
     race
    0.94
     raced
    0.90
     races
    0.86
     barre
    0.85
     plo
    0.83
     hur
    0.79
     sau
    0.79
    Activations Density 0.316%

    No Known Activations