© 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. 21-GEMMASCOPE-RES-16K
    11. 3286
    Prev
    Next
    INDEX
    Explanations

    technical terms and mathematical notation related to process optimization and algorithmic methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.69
    featureID
    -0.53
     estekak
    -0.52
     Audiodateien
    -0.52
    ագրություններ
    -0.51
    ).}
    -0.50
    ."]
    -0.49
    .")]
    -0.48
    УДК
    -0.48
    Capítulo
    -0.47
    POSITIVE LOGITS
     n
    1.24
     N
    1.06
    n
    0.98
    N
    0.92
     nth
    0.91
    getN
    0.86
    ｎ
    0.86
    Nth
    0.74
     autant
    0.74
     k
    0.70
    Activations Density 1.060%

    No Known Activations