© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    6. 2892
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and logical constructs within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIAF
    -0.77
    SharedDtor
    -0.66
    ?";
    -0.65
    ?");
    -0.60
     */;
    -0.58
     VIDEOTAPE
    -0.58
    ’).
    -0.58
    +```
    -0.57
    CascadeType
    -0.57
    SPONSORED
    -0.56
    POSITIVE LOGITS
     which
    1.31
    which
    1.08
     Which
    1.01
    Which
    0.97
     WHICH
    0.95
    hich
    0.75
    ซึ่ง
    0.67
     vilket
    0.64
     ซึ่ง
    0.64
     což
    0.62
    Activations Density 0.668%

    No Known Activations