© 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. 1-GEMMASCOPE-RES-16K
    6. 10115
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and medical contexts involving diagnostics and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.61
     disponibilités
    -0.54
     AssemblyCulture
    -0.53
    Datuak
    -0.49
    jsxFileName
    -0.47
    Mojo
    -0.47
     виправивши
    -0.47
    Categoría
    -0.44
     sommeil
    -0.44
    AccessorTable
    -0.43
    POSITIVE LOGITS
     RS
    1.38
     RB
    1.37
     RL
    1.34
     RR
    1.33
     RW
    1.33
     RC
    1.30
     RM
    1.27
     RH
    1.26
     RK
    1.26
     RP
    1.25
    Activations Density 1.900%

    No Known Activations