© 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. 5838
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or approval

    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
    vermögen
    -0.53
     Leip
    -0.47
    まさに
    -0.47
    Loyalty
    -0.47
    Ors
    -0.47
    ORN
    -0.47
    еремо
    -0.46
     réputation
    -0.46
     keres
    -0.46
    ेर
    -0.46
    POSITIVE LOGITS
     okay
    1.78
     alright
    1.75
     OK
    1.68
     OKAY
    1.60
     ok
    1.59
     Alright
    1.56
    alright
    1.56
    okay
    1.52
     Okay
    1.46
    Okay
    1.46
    Activations Density 0.224%

    No Known Activations