© 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. 4-GEMMASCOPE-RES-16K
    6. 15684
    Prev
    Next
    INDEX
    Explanations

    instances of the word "knew" or its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gill
    -0.69
     Tos
    -0.66
    TEntity
    -0.65
     Linton
    -0.65
     Efforts
    -0.64
    popd
    -0.62
    gemeinde
    -0.61
    ftest
    -0.61
    бочки
    -0.60
     Schiller
    -0.60
    POSITIVE LOGITS
     knows
    2.01
     knew
    1.95
    knew
    1.86
     know
    1.85
    knows
    1.82
     Knows
    1.80
    know
    1.73
     KNOW
    1.73
     Knew
    1.70
     Know
    1.70
    Activations Density 0.082%

    No Known Activations