© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6224
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate mutual inclusion or comparison

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

    occurrences of the word "both" used as a grammatical connector.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     rayures
    -0.53
    ozo
    -0.50
     Erskine
    -0.49
    stunde
    -0.49
     Fayette
    -0.49
     Ornament
    -0.48
    ModelAdmin
    -0.48
     createDate
    -0.48
     Hye
    -0.48
     Aristi
    -0.48
    POSITIVE LOGITS
    Both
    1.13
     Both
    1.07
     both
    1.07
     BOTH
    1.03
    both
    1.01
    BOTH
    0.94
     Beide
    0.82
     beider
    0.77
    Neither
    0.74
    Ambos
    0.71
    Activations Density 0.103%

    No Known Activations