© 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. 22-GEMMASCOPE-RES-16K
    11. 13664
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the word "True."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "True" followed by verification/boolean context

    np_acts-logits-general · gemini-2.0-flash

    True followed by capitalized words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppBundle
    -0.66
    yntaxException
    -0.63
    ⓧ
    -0.60
    tagHelperRunner
    -0.58
    einem
    -0.55
     Vedi
    -0.52
     busiest
    -0.52
    topics
    -0.51
     Cuatro
    -0.51
    DeleteBehavior
    -0.51
    POSITIVE LOGITS
     believers
    0.83
     False
    0.82
    False
    0.78
     believer
    0.77
     colors
    0.68
    false
    0.67
     True
    0.66
     blue
    0.66
    stdbool
    0.65
     false
    0.64
    Activations Density 0.083%

    No Known Activations