© 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. 12561
    Prev
    Next
    INDEX
    Explanations

    phrases and structures indicating existence or presence

    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
     lloc
    -0.51
    stuffs
    -0.50
     itſelf
    -0.49
    Lähteet
    -0.48
    WebpackPlugin
    -0.48
    ́t
    -0.47
     MenuView
    -0.47
    ωση
    -0.46
     jsPsych
    -0.45
     engineers
    -0.45
    POSITIVE LOGITS
     ones
    1.01
     Ones
    0.78
     theirs
    0.71
    Ones
    0.70
     others
    0.66
    AutoScale
    0.66
     them
    0.65
     quelli
    0.64
    Others
    0.62
     Others
    0.60
    Activations Density 0.443%

    No Known Activations