© 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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8392
    Prev
    Next
    INDEX
    Explanations

    references to groups or categories of different entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meisten
    -0.35
    ])))
    -0.35
    unehmen
    -0.34
    ))))
    -0.31
    tably
    -0.30
    presence
    -0.29
    )))));
    -0.29
    together
    -0.29
     此
    -0.29
    status
    -0.28
    POSITIVE LOGITS
     companies
    0.81
     diseases
    0.79
     gadgets
    0.76
     organisations
    0.74
    henswürdigkeiten
    0.74
     organizations
    0.73
     youtuber
    0.71
     novels
    0.71
     instruments
    0.70
     websites
    0.70
    Activations Density 1.902%

    No Known Activations