© 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. 6252
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or action

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

    polite requests or phrases like "Please let us know" or "Please help me".

    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
     GSC
    -0.45
    SharedCtor
    -0.44
     ICM
    -0.44
    Карьера
    -0.41
     cdti
    -0.40
     Mountain
    -0.40
     mountain
    -0.40
    んでる
    -0.39
     NCP
    -0.39
    MCM
    -0.39
    POSITIVE LOGITS
     please
    1.02
    please
    0.99
    Please
    0.99
     Please
    0.98
    PLEASE
    0.81
     PLEASE
    0.81
     Bitte
    0.80
    Bitte
    0.80
     bitte
    0.75
     Kindly
    0.70
    Activations Density 0.040%

    No Known Activations