© 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. 20-GEMMASCOPE-RES-16K
    11. 15412
    Prev
    Next
    INDEX
    Explanations

    references to threats or dangers in various contexts

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

    Words/phrases related to "threat" or "danger."

    np_acts-logits-general · gemini-2.0-flash

    pose a threat or danger

    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
    กรรม
    -0.54
     getItemId
    -0.49
     canons
    -0.47
     encarga
    -0.46
     Sorg
    -0.46
    кономі
    -0.46
     constipation
    -0.45
    timmung
    -0.45
     spra
    -0.44
    HasMaxLength
    -0.44
    POSITIVE LOGITS
     threat
    2.76
    threat
    2.48
     threats
    2.48
     Threat
    2.40
    Threat
    2.34
     Threats
    2.21
     threaten
    2.17
     threatening
    2.13
     threatened
    2.04
     danger
    2.04
    Activations Density 0.288%

    No Known Activations