© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1023
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that contain discussions about ratios and proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brun
    -0.60
    xca
    -0.60
    dep
    -0.59
     Eisenberg
    -0.59
    =""/>
    -0.59
    د
    -0.59
    Nec
    -0.58
     Paglinawan
    -0.58
     Mey
    -0.57
    PEND
    -0.57
    POSITIVE LOGITS
     ratio
    2.78
     Ratio
    2.67
     ratios
    2.63
     RATIO
    2.55
    ratio
    2.45
    Ratio
    2.40
     Ratios
    2.38
    ratios
    2.18
    RATIO
    1.93
     proportion
    1.54
    Activations Density 0.097%

    No Known Activations