© 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. 9600
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize conclusions or important points in arguments

    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
     >=",
    -0.78
     <>",
    -0.74
    ❷
    -0.73
    oredCriteria
    -0.72
    RTDA
    -0.70
    WireFormatLite
    -0.69
    ">//
    -0.67
    спеди
    -0.67
    tonode
    -0.66
     BytesLike
    -0.63
    POSITIVE LOGITS
     ultimately
    1.74
     Ultimately
    1.67
    Ultimately
    1.63
     ultimate
    1.28
     uiteindelijk
    1.20
     letzt
    1.00
    ultimate
    0.97
    結局
    0.96
    ulti
    0.96
    最终
    0.92
    Activations Density 0.247%

    No Known Activations