© 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. 3-GEMMASCOPE-RES-16K
    11. 12600
    Prev
    Next
    INDEX
    Explanations

    the character "Ko" and its variations, indicating its significance in the context

    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
     Hund
    -0.64
    clav
    -0.60
     Cach
    -0.59
    CLOCK
    -0.59
    ting
    -0.58
    Lanz
    -0.57
    mentary
    -0.57
     cư
    -0.56
     conversation
    -0.56
    purl
    -0.56
    POSITIVE LOGITS
    Ko
    2.66
     Ko
    2.63
     ko
    2.58
    ko
    2.54
    KO
    2.03
     KO
    1.84
     Koe
    1.33
     Koval
    1.28
    Koz
    1.23
    Koala
    1.20
    Activations Density 0.080%

    No Known Activations