© 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. 20-GEMMASCOPE-RES-16K
    6. 8464
    Prev
    Next
    INDEX
    Explanations

    prominent names and titles associated with authoritative figures or speakers

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

    Names of people

    np_acts-logits-general · gemini-2.0-flash

    first names

    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
     redor
    -0.50
     fato
    -0.49
     CreateTagHelper
    -0.49
     đo
    -0.47
    oudre
    -0.47
     Dunlap
    -0.47
    oredCriteria
    -0.47
     promedio
    -0.47
    polazione
    -0.46
     chi̍t
    -0.45
    POSITIVE LOGITS
     Efq
    0.79
    
    0.74
     Theſe
    0.69
     Majefty
    0.67
     Chriftian
    0.66
     OBE
    0.62
     Ouv
    0.62
     Forumite
    0.62
     actionMode
    0.60
     Allez
    0.60
    Activations Density 0.168%

    No Known Activations