© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7530
    Prev
    Next
    INDEX
    Explanations

    specific letters or letter combinations that represent certain variables or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    L
    -0.97
    o
    -0.94
    H
    -0.94
    i
    -0.93
    V
    -0.91
    v
    -0.91
    U
    -0.90
    W
    -0.89
    D
    -0.89
    M
    -0.89
    POSITIVE LOGITS
    ]")]
    1.19
    NewUrlParser
    1.15
    وأضاف
    1.09
    NameInMap
    1.06
    andafter
    1.04
    iffance
    1.03
    ratulations
    0.99
    ighbor
    0.99
    polation
    0.99
     ProtoMessage
    0.99
    Activations Density 0.622%

    No Known Activations