© 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. 8-GEMMASCOPE-RES-16K
    6. 7845
    Prev
    Next
    INDEX
    Explanations

    elements related to matrix operations and linear algebra

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ligg
    -0.53
     Resolution
    -0.51
    bisk
    -0.49
    vud
    -0.48
     disfru
    -0.48
    Resolution
    -0.47
     Piv
    -0.47
    platt
    -0.47
    
    -0.45
     Neglect
    -0.45
    POSITIVE LOGITS
    MLLoader
    1.00
    extAlignment
    0.83
    currentColor
    0.82
    ModelAdmin
    0.78
    UnusedPrivate
    0.76
    webElementXpaths
    0.70
     BoxDecoration
    0.69
    UpInside
    0.68
    DataMember
    0.67
     GenerationType
    0.67
    Activations Density 0.185%

    No Known Activations