© 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. 18-GEMMASCOPE-RES-16K
    11. 4216
    Prev
    Next
    INDEX
    Explanations

    references to specific types of diabetes and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding or related to "type"

    np_acts-logits-general · gemini-2.0-flash

    type of classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.73
    makeConstraints
    -0.58
     AppBar
    -0.57
    mapStateToProps
    -0.56
     imperio
    -0.52
     Gatwick
    -0.52
    ρευ
    -0.50
     bezeichneter
    -0.49
    Autoritní
    -0.49
     Sequel
    -0.49
    POSITIVE LOGITS
     TextInputType
    0.84
     getType
    0.80
    XmlType
    0.75
     AssemblyCulture
    0.74
    faces
    0.74
     AssemblyProduct
    0.73
     setType
    0.71
     TokenType
    0.71
     userType
    0.71
    RTGC
    0.70
    Activations Density 0.301%

    No Known Activations