© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9512
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly pertaining to measurements and statistical data

    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
     CSP
    -0.61
    CSP
    -0.58
    celi
    -0.57
    ↵↵
    -0.56
    őség
    -0.53
    コモ
    -0.53
    ital
    -0.52
    cional
    -0.51
    vms
    -0.50
    лъ
    -0.50
    POSITIVE LOGITS
    8
    1.25
    ValueStyle
    0.95
     EIGHT
    0.95
    7
    0.95
     Eighth
    0.94
    9
    0.94
    eight
    0.94
     Eighty
    0.94
     Eight
    0.91
    TypedDataSet
    0.89
    Activations Density 0.197%

    No Known Activations