© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9100
    Prev
    Next
    INDEX
    Explanations

    terms associated with danger or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.76
     المعيارى
    -0.71
    adaptiveStyles
    -0.67
     claro
    -0.65
     clara
    -0.64
     pageContext
    -0.64
    ânsito
    -0.63
    Clik
    -0.62
    ----</
    -0.60
    MigrationBuilder
    -0.60
    POSITIVE LOGITS
     dangerous
    1.46
     harmful
    1.38
    dangerous
    1.32
     hazardous
    1.28
    Dangerous
    1.24
     deadly
    1.24
     lethal
    1.24
     Dangerous
    1.17
     destructive
    1.10
    Deadly
    1.09
    Activations Density 0.288%

    No Known Activations