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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2437
    Prev
    Next
    INDEX
    Explanations

    the presence and frequency of the word "in" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    AxisSize
    -0.79
    geable
    -0.73
    omeness
    -0.71
    enegger
    -0.70
    ganza
    -0.69
     Wadsworth
    -0.69
    ladolid
    -0.68
    OSC
    -0.68
    adecimal
    -0.67
    ondag
    -0.67
    POSITIVE LOGITS
    in
    2.52
    IN
    2.09
    ins
    1.48
    nin
    1.39
    tin
    1.28
    inin
    1.27
    vin
    1.26
    rin
    1.25
    hin
    1.19
    inn
    1.18
    Activations Density 0.221%

    No Known Activations