© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9879
    Prev
    Next
    INDEX
    Explanations

    references to severe medical conditions or adverse effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUp
    -0.89
    Clik
    -0.70
    躇
    -0.70
     fak
    -0.66
     AUSSI
    -0.66
     Dux
    -0.64
    ט
    -0.63
    wirtschaft
    -0.63
    ?>">
    -0.63
    roxene
    -0.63
    POSITIVE LOGITS
     severe
    2.30
     Severe
    2.27
    Severe
    2.22
    severe
    2.19
     severity
    1.91
     sever
    1.78
     SEVER
    1.76
    SEVERE
    1.76
     Severity
    1.73
     severely
    1.69
    Activations Density 0.137%

    No Known Activations