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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8512
    Prev
    Next
    INDEX
    Explanations

    biological or technical terms related to classification metrics and experimental protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikea
    -0.44
    يكب
    -0.42
     yarar
    -0.37
     Lund
    -0.36
     Judd
    -0.35
     görüş
    -0.35
     känd
    -0.35
    addGroup
    -0.35
     karş
    -0.34
     nahilalakip
    -0.34
    POSITIVE LOGITS
     TP
    0.71
    Personendaten
    0.68
     InputDecoration
    0.68
    tp
    0.68
     turtle
    0.66
    TP
    0.65
    turtle
    0.65
    RenderAtEndOf
    0.63
     tp
    0.62
    Turtle
    0.62
    Activations Density 0.391%

    No Known Activations