© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    numerical measurements and quantities, particularly in relation to land and volume

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

    numerical measurements and specifications, especially quantities with units.

    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
     utafitiHapana
    -0.73
     <<<<<<<<<<<<<<
    -0.68
    fjspx
    -0.60
    VYMaps
    -0.59
     للاسماء
    -0.58
     pouvoit
    -0.57
    Rüyada
    -0.56
    <unused52>
    -0.56
    <unused16>
    -0.55
    <unused68>
    -0.55
    POSITIVE LOGITS
    kháu
    0.44
    enumi
    0.42
    )):
    0.37
     Савезне
    0.36
    )));
    0.34
    )):
    0.34
    prüche
    0.34
     Tem
    0.34
     wym
    0.33
     informée
    0.33
    Activations Density 0.060%

    No Known Activations