© 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. 4438
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and chemical processes, particularly focusing on functions and interactions involving proteins and substances

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

    after common words like "the", "of", "and", "including"

    np_acts-logits-general · gemini-2.0-flash

    of medical condition information

    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
     sm
    -0.36
    UIFont
    -0.36
     suzuki
    -0.35
    stri
    -0.35
    pic
    -0.34
    inf
    -0.33
    grin
    -0.33
    gr
    -0.33
    AFC
    -0.33
     adam
    -0.32
    POSITIVE LOGITS
     resourceCulture
    0.66
    verwijspagina
    0.64
     ivelany
    0.63
    DockStyle
    0.61
     мәкал
    0.59
    Климаты
    0.57
    ")]
    
    0.56
    kwds
    0.56
    "]
    
    0.56
    Хьажоргаш
    0.55
    Activations Density 1.176%

    No Known Activations