© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7306
    Prev
    Next
    INDEX
    Explanations

    occurrences of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poffible
    -0.49
     reaſon
    -0.47
    väg
    -0.47
     föruts
    -0.46
     cauſe
    -0.45
     ſche
    -0.45
     fubject
    -0.45
     occur
    -0.44
     gräns
    -0.44
     neceff
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.72
    XmlAccessorType
    0.65
     незавершена
    0.59
    MessageOf
    0.57
     дописавши
    0.56
    倆
    0.54
    tagext
    0.52
    帖最后由
    0.52
    хьтан
    0.52
     AttributeSet
    0.51
    Activations Density 0.334%

    No Known Activations