© 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. 1-GEMMASCOPE-RES-16K
    6. 6827
    Prev
    Next
    INDEX
    Explanations

    references to media literacy and educational topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.68
    WithIOException
    -0.65
     invokingState
    -0.65
     تضيفلها
    -0.63
    
    -0.63
    utilisons
    -0.63
    ナメント
    -0.61
    ArrowToggle
    -0.59
     AssemblyCulture
    -0.58
    issauga
    -0.57
    POSITIVE LOGITS
     Jam
    0.76
     BBC
    0.69
    jam
    0.67
    Jam
    0.66
     jam
    0.62
     ABC
    0.62
     "..\..\..\
    0.59
    BBC
    0.58
     jams
    0.57
    pyx
    0.55
    Activations Density 2.067%

    No Known Activations