© 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. 10-GEMMASCOPE-RES-16K
    11. 10985
    Prev
    Next
    INDEX
    Explanations

    terms related to boolean variables and conditions in programming

    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
     Spence
    -0.77
     <>",
    -0.75
     Kün
    -0.74
     ")");
    -0.72
     câte
    -0.71
     Monfieur
    -0.70
     Schmid
    -0.70
     către
    -0.68
     viață
    -0.67
     NavController
    -0.67
    POSITIVE LOGITS
     bool
    1.31
    bool
    1.19
    getBoolean
    1.11
     Bool
    1.08
    oolean
    1.08
    stdbool
    1.06
     boolean
    1.02
    Bool
    1.00
    SetBool
    0.98
    putBoolean
    0.96
    Activations Density 0.032%

    No Known Activations