© 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. 11-GEMMASCOPE-RES-16K
    11. 6736
    Prev
    Next
    INDEX
    Explanations

    instances of the word "false" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.83
     Hecht
    -0.81
    زیین
    -0.79
     referenties
    -0.75
    +#+#
    -0.75
    EndContext
    -0.74
    supra
    -0.73
     chré
    -0.73
    akesh
    -0.72
     aufnehmen
    -0.71
    POSITIVE LOGITS
     false
    1.10
    false
    0.96
     False
    0.94
    False
    0.88
     fals
    0.86
    GraphicsUnit
    0.85
    FALSE
    0.84
     FALSE
    0.80
    ation
    0.78
     falsely
    0.78
    Activations Density 0.089%

    No Known Activations