© 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. 15-GEMMASCOPE-RES-16K
    6. 7924
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time frames or intervals

    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
    \",\
    -0.51
    pak
    -0.46
    !");
    -0.43
    ={<
    -0.42
    ól
    -0.40
    pb
    -0.39
    lwz
    -0.39
     };
    
    -0.39
     Domin
    -0.39
     gro
    -0.38
    POSITIVE LOGITS
     periods
    0.86
    tvguidetime
    0.84
     period
    0.83
    periods
    0.81
    enderror
    0.79
     panahon
    0.79
     Periods
    0.78
     typelib
    0.77
    LookAnd
    0.76
    Periods
    0.74
    Activations Density 0.247%

    No Known Activations