© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13849
    Prev
    Next
    INDEX
    Explanations

    terms related to quality, specifically in the context of sound and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -1.00
     EconPapers
    -0.83
    )");
    
    -0.83
    Демографія
    -0.81
     >=",
    -0.80
    migrationBuilder
    -0.80
    MessageOf
    -0.79
     ExecuteAsync
    -0.79
    ]";
    -0.79
     autorytatywna
    -0.76
    POSITIVE LOGITS
    tes
    0.60
     P
    0.48
    เพ
    0.45
     i
    0.44
    P
    0.44
     D
    0.44
     I
    0.43
    F
    0.42
     a
    0.42
     liné
    0.42
    Activations Density 0.409%

    No Known Activations