© 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. 18-GEMMASCOPE-RES-16K
    11. 14180
    Prev
    Next
    INDEX
    Explanations

    references to accidental or unintentional actions

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

    Accidents or chance occurrences

    np_acts-logits-general · gemini-2.0-flash

    by chance or accident

    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
     ModelExpression
    -0.94
    __':
    -0.74
     createState
    -0.71
    "},
    -0.68
    ]$}
    -0.68
    WebElementEntity
    -0.66
    óngase
    -0.66
    "],
    -0.64
    ()]
    -0.63
    ContentAsync
    -0.63
    POSITIVE LOGITS
     accident
    2.11
     accidental
    2.09
     accidentally
    2.04
    accident
    1.91
     Accidental
    1.83
     Accident
    1.79
    Accidental
    1.78
    Accident
    1.71
     accidente
    1.69
     unintentional
    1.68
    Activations Density 0.319%

    No Known Activations