© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6807
    Prev
    Next
    INDEX
    Explanations

    instances of the word "contrast" 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    よいよ
    -0.60
    daje
    -0.58
    LAYER
    -0.57
    ########.
    -0.55
    jvm
    -0.53
     Flyer
    -0.53
    נוּ
    -0.51
    }{*}{
    -0.51
     industriale
    -0.51
    uge
    -0.51
    POSITIVE LOGITS
     complement
    1.25
     compliment
    1.18
     contrast
    1.12
    compli
    1.09
     Compli
    1.06
     complimentary
    1.03
    complement
    1.02
    contrast
    1.00
    Complement
    1.00
     Complement
    1.00
    Activations Density 0.077%

    No Known Activations