© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15476
    Prev
    Next
    INDEX
    Explanations

    terms related to hydration metrics in plants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RR
    -1.06
     RI
    -1.01
     ri
    -0.92
     RM
    -0.90
     Р
    -0.87
     R
    -0.86
     Ri
    -0.86
     RD
    -0.85
     RE
    -0.83
     RC
    -0.80
    POSITIVE LOGITS
    rate
    0.74
     LUMP
    0.65
    raw
    0.61
    row
    0.57
    rated
    0.56
    rates
    0.56
    rating
    0.55
    ratio
    0.55
    rare
    0.55
    kloped
    0.54
    Activations Density 0.727%

    No Known Activations