© 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. 15-GEMMASCOPE-RES-16K
    11. 6033
    Prev
    Next
    INDEX
    Explanations

    attributes and styles related to user interface elements in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteMapping
    -0.69
    存于互联网档案馆
    -0.66
    propy
    -0.59
    subpackage
    -0.58
     estekak
    -0.56
    UserScript
    -0.54
    toContain
    -0.54
    getExternal
    -0.53
     Geografía
    -0.53
    fastjson
    -0.52
    POSITIVE LOGITS
    CGRectMake
    0.62
    ArrowToggle
    0.59
     CGRectMake
    0.59
    //
    0.58
    AnchorStyles
    0.56
    CppMethod
    0.54
     MonoBehaviour
    0.54
    BeginContext
    0.53
     createSprite
    0.51
     pylint
    0.51
    Activations Density 0.040%

    No Known Activations