Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12593
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal journeys and individual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atività
    -0.48
    uría
    -0.48
    Handled
    -0.47
     killed
    -0.47
    rcParams
    -0.46
     Gelen
    -0.45
     ब्रेकडाउन
    -0.45
     Marxism
    -0.44
     الحره
    -0.43
     DEAD
    -0.43
    POSITIVE LOGITS
     journey
    2.32
    journey
    2.03
     Journey
    1.79
    Journey
    1.75
     journeys
    1.72
     JOURNEY
    1.69
     voyage
    1.44
     adventure
    1.34
     viaje
    1.30
     perjalanan
    1.27
    Activations Density 0.184%

    No Known Activations