© 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. 7267
    Prev
    Next
    INDEX
    Explanations

    descriptions and evaluations of feature detection methods and their performance metrics

    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
     Reverso
    -0.56
     '\\;'
    -0.56
    fillType
    -0.56
    DialogTitle
    -0.53
    ToBounds
    -0.51
    nodoc
    -0.51
    alkin
    -0.49
    enterOuterAlt
    -0.49
     taping
    -0.49
    ResumeLayout
    -0.49
    POSITIVE LOGITS
     feature
    1.33
     features
    1.30
    feature
    1.17
     Features
    1.14
     Feature
    1.13
    features
    1.12
     FEATURE
    1.08
    Feature
    1.08
    Features
    1.02
     FEATURES
    0.97
    Activations Density 0.807%

    No Known Activations