© 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. 23-GEMMASCOPE-RES-16K
    6. 7228
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and punctuation, likely indicating data such as timestamps or code-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.64
    PositiveButton
    -0.58
     ModelExpression
    -0.53
    UnsafeEnabled
    -0.51
    chenta
    -0.51
    ⓧ
    -0.51
     للاسماء
    -0.46
     विश्वसनीयता
    -0.46
    ISupport
    -0.46
    quante
    -0.46
    POSITIVE LOGITS
    BeginContext
    0.56
    httphttps
    0.55
     domestique
    0.53
     interessi
    0.52
     magique
    0.51
    atv
    0.51
     klock
    0.50
    ług
    0.49
    abetes
    0.49
    ToBounds
    0.48
    Activations Density 0.200%

    No Known Activations