© 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. 13163
    Prev
    Next
    INDEX
    Explanations

    sentences containing quotes or reported speech

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

    preceding quotations or reported speech

    np_acts-logits-general · gemini-2.0-flash

    apart, majority, Nigerians

    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
    utilisons
    -0.61
    complexType
    -0.57
    TextWatcher
    -0.56
     useCallback
    -0.55
    PointerException
    -0.52
    المصدر
    -0.52
     rodríguez
    -0.50
     ¦
    -0.50
     fucked
    -0.50
     namin
    -0.50
    POSITIVE LOGITS
     apart
    0.93
    apart
    0.86
    Apart
    0.78
     Apart
    0.78
    Majority
    0.63
     Nigerians
    0.62
    efforts
    0.60
     contrary
    0.60
     notwithstanding
    0.60
     majority
    0.59
    Activations Density 0.037%

    No Known Activations