© 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. 20-GEMMASCOPE-RES-16K
    11. 8529
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and blame in various contexts

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

    Attributing blame or responsibility

    np_acts-logits-general · gemini-2.0-flash

    fault, cause, or source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.48
     cappuccio
    -0.46
    gameserver
    -0.46
    onOptions
    -0.46
    osaurus
    -0.45
     собою
    -0.45
    enné
    -0.42
    aimana
    -0.42
    Override
    -0.41
    RequestBody
    -0.41
    POSITIVE LOGITS
     blame
    2.28
     Blame
    2.01
     blamed
    2.00
    blame
    1.92
     blaming
    1.91
     blames
    1.89
    Blame
    1.85
     attributed
    1.68
     attribute
    1.57
     attribution
    1.52
    Activations Density 0.396%

    No Known Activations