© 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. 5255
    Prev
    Next
    INDEX
    Explanations

    terms related to danger and risk

    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
    sunter
    -0.40
    ************
    -0.39
    ophon
    -0.39
     Scro
    -0.38
    締め
    -0.38
     Shil
    -0.38
     unresolved
    -0.37
    interopRequire
    -0.37
     cob
    -0.37
     Newell
    -0.37
    POSITIVE LOGITS
     danger
    2.73
     risk
    2.52
     Danger
    2.36
    Danger
    2.34
    danger
    2.31
    risk
    2.30
     dangers
    2.25
     peligro
    2.23
     Risk
    2.20
     risks
    2.19
    Activations Density 0.235%

    No Known Activations