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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12580
    Prev
    Next
    INDEX
    Explanations

    statements regarding causation and justification in complex scenarios

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

    Causation or origin of an event

    np_acts-logits-general · gemini-2.0-flash

    cause and intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    licon
    -0.52
     Hoon
    -0.49
     riesgo
    -0.46
    lite
    -0.45
    MsgBox
    -0.43
    utnik
    -0.42
     Danger
    -0.41
     bother
    -0.40
    Danger
    -0.40
     rischio
    -0.40
    POSITIVE LOGITS
     accidental
    0.92
     caused
    0.80
    caused
    0.76
     Caused
    0.71
     intentional
    0.71
    人为
    0.70
    MemoryWarning
    0.69
     exogenous
    0.69
     accidentally
    0.68
     Accidental
    0.68
    Activations Density 0.699%

    No Known Activations