© 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. 693
    Prev
    Next
    INDEX
    Explanations

    expressions of indifference or casual acceptance

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

    filler words and conversational phrases like "whatever".

    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
     Jiao
    -0.52
     Riau
    -0.48
    DMC
    -0.46
     Racine
    -0.46
    adaptiveStyles
    -0.45
     Peanuts
    -0.45
     Oates
    -0.45
     Diagnostics
    -0.45
     Ismail
    -0.44
    Race
    -0.44
    POSITIVE LOGITS
    whatever
    0.85
     whatever
    0.82
    Whatever
    0.73
     Whatever
    0.71
    atever
    0.69
    whenever
    0.68
     tartalomajánló
    0.67
     wherever
    0.63
    ever
    0.63
     whichever
    0.61
    Activations Density 0.031%

    No Known Activations