© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1672
    Prev
    Next
    INDEX
    Explanations

    references to materials with electronic and magnetic properties

    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
    WaitGroup
    -0.64
    TagHelper
    -0.62
     BorderSide
    -0.59
    Kaieteur
    -0.58
    RectangleBorder
    -0.54
    (!__
    -0.54
    getActiveSheet
    -0.53
    InputBorder
    -0.52
    ExecuteReader
    -0.52
    protoimpl
    -0.50
    POSITIVE LOGITS
     propOrder
    0.70
     ABO
    0.64
    ABO
    0.63
     substitution
    0.61
     compositions
    0.61
     stoichio
    0.61
     Sr
    0.60
    Gdx
    0.59
     Substitution
    0.57
     Riet
    0.56
    Activations Density 1.153%

    No Known Activations