© 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. 20-GEMMASCOPE-RES-16K
    11. 6830
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental regulation and public health measures

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

    prevention or avoidance

    np_acts-logits-general · gemini-2.0-flash

    preventing negative outcomes

    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
    ArgsConstructor
    -0.85
     nahilalakip
    -0.74
    LookAnd
    -0.65
    StructEnd
    -0.65
     ModelExpression
    -0.64
    providedIn
    -0.64
    цездатний
    -0.64
    IVEREF
    -0.62
     betweenstory
    -0.62
    UnusedPrivate
    -0.60
    POSITIVE LOGITS
     avoid
    2.38
     avoiding
    2.37
     prevent
    2.32
    avoid
    2.30
     avoided
    2.30
     Avoiding
    2.22
    prevent
    2.20
     prevention
    2.19
     avoids
    2.18
     Avoid
    2.15
    Activations Density 0.762%

    No Known Activations