© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6163
    Prev
    Next
    INDEX
    Explanations

    chemical and material related symbols and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patterson
    -0.46
    assertTrue
    -0.43
     permu
    -0.42
     Gey
    -0.40
    .~\
    -0.40
    ➔
    -0.40
    hofer
    -0.40
    settings
    -0.40
    Â
    -0.40
     Stewart
    -0.39
    POSITIVE LOGITS
    xc
    0.80
    Hec
    0.78
    kc
    0.77
    ac
    0.74
    kec
    0.74
    icec
    0.73
     Hec
    0.72
    Xc
    0.71
    c
    0.71
    ec
    0.71
    Activations Density 1.554%

    No Known Activations