© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7535
    Prev
    Next
    INDEX
    Explanations

    terms associated with metabolic processes and their regulation

    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
     Hoo
    -0.88
    Hoo
    -0.87
     Bin
    -0.83
     BIN
    -0.81
     Hoover
    -0.78
    Bin
    -0.75
     Susie
    -0.75
     Bobby
    -0.72
     Walla
    -0.68
    Bobby
    -0.67
    POSITIVE LOGITS
     Johnson
    1.35
    Johnson
    1.19
     JOHNSON
    1.19
     johnson
    1.04
    johnson
    1.02
    NSON
    0.86
     Erickson
    0.82
     Andrea
    0.81
    JOH
    0.78
     Judson
    0.75
    Activations Density 1.567%

    No Known Activations