© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 529
    Prev
    Next
    INDEX
    Explanations

    references to various types of risks and potential harm

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

    "risk" or "risks"

    np_acts-logits-general · gemini-2.0-flash

    risk of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     telefoon
    -0.48
     laikā
    -0.43
     StringTokenizer
    -0.43
     boneca
    -0.43
    itele
    -0.43
    Cartney
    -0.42
     चाहिए
    -0.41
    della
    -0.41
     seragam
    -0.41
     stuffed
    -0.40
    POSITIVE LOGITS
     risk
    1.39
    Risk
    1.32
     Risk
    1.31
    risk
    1.29
     risks
    1.22
     RISK
    1.17
     Risks
    1.15
    RISK
    1.15
    risks
    1.05
    Risks
    1.04
    Activations Density 0.154%

    No Known Activations