© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7113
    Prev
    Next
    INDEX
    Explanations

    warnings and safety instructions related to medication use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.45
     justement
    -0.43
    ="@+
    -0.42
    Così
    -0.42
     AssemblyVersion
    -0.40
    semantics
    -0.40
     tweaked
    -0.40
    Carriera
    -0.39
     soprav
    -0.38
     همین
    -0.38
    POSITIVE LOGITS
     Never
    0.94
    Never
    0.93
     never
    0.87
     Avoid
    0.87
     NEVER
    0.84
    NEVER
    0.81
    Avoid
    0.81
     Always
    0.79
    Always
    0.78
    never
    0.76
    Activations Density 0.413%

    No Known Activations