© 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. 17-GEMMASCOPE-RES-16K
    11. 7882
    Prev
    Next
    INDEX
    Explanations

    mentions of "feature" in various contexts related to functionality and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PVA
    -0.99
    ILON
    -0.89
     clearColor
    -0.89
    ioutil
    -0.85
    protoimpl
    -0.83
     ALP
    -0.82
     GenerationType
    -0.81
     pregunto
    -0.81
     Мексичка
    -0.81
    idp
    -0.80
    POSITIVE LOGITS
     features
    1.52
     feature
    1.36
     Features
    1.25
    Features
    1.24
    features
    1.21
     FEATURE
    1.19
     Feature
    1.12
     FEATURES
    1.11
    feature
    1.08
    Feature
    1.07
    Activations Density 0.046%

    No Known Activations