© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5125
    Prev
    Next
    INDEX
    Explanations

    assertions of dishonesty or deception

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

    Statements of untruth/falsehood

    np_acts-logits-general · gemini-2.0-flash

    identifying falsehoods or deception

    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
     AssemblyProduct
    -0.83
     AssemblyTitle
    -0.80
    autoreleasepool
    -0.73
     виправивши
    -0.72
    })));
    -0.69
    reportWebVitals
    -0.69
    +#+
    -0.68
    Tikang
    -0.68
    IBarButtonItem
    -0.67
     onOptions
    -0.66
    POSITIVE LOGITS
     false
    2.17
     fake
    1.94
     False
    1.84
     falsehood
    1.84
    false
    1.83
    False
    1.73
     untrue
    1.69
     lie
    1.69
     fals
    1.66
     Fake
    1.66
    Activations Density 1.053%

    No Known Activations