© 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. 1-GEMMASCOPE-RES-16K
    11. 15617
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating temporal or conditional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gnition
    -1.10
    frastructure
    -0.94
    FTFY
    -0.93
    disambiguation
    -0.92
    bibfield
    -0.87
    ratulations
    -0.87
    Carcinogenicity
    -0.86
    tymologie
    -0.86
    ftance
    -0.86
    STRUCTOR
    -0.85
    POSITIVE LOGITS
    in
    0.99
    by
    0.98
    for
    0.95
    at
    0.90
    of
    0.90
    For
    0.90
    per
    0.89
    be
    0.85
    Or
    0.85
    is
    0.83
    Activations Density 0.425%

    No Known Activations