© 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. 11-GEMMASCOPE-RES-16K
    11. 1622
    Prev
    Next
    INDEX
    Explanations

    terms related to safety regulations and compliance in industrial settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfeiriadau
    -0.63
    anskje
    -0.60
    \{\\
    -0.56
    quartier
    -0.55
    thâu
    -0.53
    WithIOException
    -0.52
    riguez
    -0.48
    lgari
    -0.48
    lccn
    -0.48
     disappointed
    -0.47
    POSITIVE LOGITS
     safety
    1.34
    safety
    1.28
     Safety
    1.24
    Safety
    1.23
     dangerous
    1.14
     unsafe
    1.13
     SAFETY
    1.11
     danger
    1.11
     Danger
    1.06
     Dangerous
    1.04
    Activations Density 0.349%

    No Known Activations