© 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. 31-GEMMASCOPE-RES-16K
    11. 2828
    Prev
    Next
    INDEX
    Explanations

    parameters related to image processing and optimization

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

    aspect ratios and numerical proportions expressed in formats like "16:9" or "4:3".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    numerical ratios and proportions expressed with colons and numbers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dafx
    -0.33
    queryInterface
    -0.30
     SEP
    -0.30
    
    -0.30
    enda
    -0.29
     CEP
    -0.29
    ipp
    -0.29
    pens
    -0.29
    au
    -0.29
    είται
    -0.28
    POSITIVE LOGITS
     aspect
    1.31
     ratio
    1.28
     ratios
    1.22
     Aspect
    1.21
     Ratio
    1.20
     Ratios
    1.13
    Aspect
    1.13
    ratio
    1.11
    aspect
    1.11
     RATIO
    1.10
    Activations Density 0.202%

    No Known Activations