© 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. 28-GEMMASCOPE-RES-16K
    6. 8254
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical studies and research methodologies

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

    before nouns

    np_acts-logits-general · gemini-2.0-flash

    situations, programs, or schemes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épaules
    -0.71
     vœux
    -0.63
     âmes
    -0.63
     lèvres
    -0.61
     bienfaits
    -0.61
     larmes
    -0.56
     dieux
    -0.54
     inconvénients
    -0.53
     prêtres
    -0.53
     enfans
    -0.49
    POSITIVE LOGITS
     setups
    0.99
     frameworks
    0.91
     programmes
    0.91
     versions
    0.90
     agendas
    0.90
     regimens
    0.90
     situations
    0.89
     programs
    0.89
     scenarios
    0.88
     schemes
    0.87
    Activations Density 3.711%

    No Known Activations