© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9447
    Prev
    Next
    INDEX
    Explanations

    references to journeys or personal stories of transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     balles
    -0.66
    srs
    -0.66
     femeninos
    -0.64
     tbs
    -0.62
    visel
    -0.61
     defaultdict
    -0.60
    ęcia
    -0.59
     Constitucional
    -0.59
     morts
    -0.59
     negar
    -0.59
    POSITIVE LOGITS
     journey
    2.34
     Journey
    2.23
     JOURNEY
    2.15
    journey
    2.09
    Journey
    2.07
     journeys
    2.06
     Journeys
    1.78
    JOUR
    1.53
    旅程
    1.37
    jour
    1.30
    Activations Density 0.058%

    No Known Activations