© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12303
    Prev
    Next
    INDEX
    Explanations

    terms related to climbing and playground equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endregion
    -0.70
     Puck
    -0.60
     Puk
    -0.60
    Canton
    -0.58
     gift
    -0.58
     Prato
    -0.57
     Bao
    -0.55
    Ответ
    -0.55
    NewGuid
    -0.55
    setPref
    -0.54
    POSITIVE LOGITS
     climbing
    1.55
     climb
    1.55
    climbing
    1.53
     Climbing
    1.51
    climb
    1.48
     climbs
    1.47
    Climbing
    1.47
    Climb
    1.47
     climbers
    1.44
     climber
    1.43
    Activations Density 0.193%

    No Known Activations