© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 7880
    Prev
    Next
    INDEX
    Explanations

    LaTeX document formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ormick
    -0.68
    RegressionTest
    -0.64
    erweise
    -0.63
     Walkover
    -0.63
    verengi
    -0.61
    toHave
    -0.60
     Stearns
    -0.59
     <<<<<<<<<<<<<<
    -0.58
    ńst
    -0.57
    írez
    -0.57
    POSITIVE LOGITS
    Font
    2.61
     Font
    1.85
    setFont
    1.40
     font
    1.38
     FONT
    1.35
    font
    1.28
    FONT
    1.26
    SetFont
    1.03
     Fontana
    1.01
    getFont
    1.00
    Activations Density 0.024%

    No Known Activations