© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5715
    Prev
    Next
    INDEX
    Explanations

    terms related to danger or potential harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.66
    }");
    -0.44
     Centen
    -0.42
     passenger
    -0.40
    onPressed
    -0.40
     getItemCount
    -0.39
    tvguidetime
    -0.38
    )");
    -0.38
    KEYCODE
    -0.38
    AndEndTag
    -0.37
    POSITIVE LOGITS
     harmful
    0.81
     dangerous
    0.77
    dangerous
    0.65
     hazardous
    0.64
    Harmful
    0.63
     AssemblyProduct
    0.61
     Harmful
    0.61
     Dangerous
    0.61
     dangereux
    0.59
     costly
    0.59
    Activations Density 0.199%

    No Known Activations