© 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. 15-GEMMASCOPE-RES-16K
    6. 7907
    Prev
    Next
    INDEX
    Explanations

    lines of code and programming functions related to state management

    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
     prz
    -0.57
    Dre
    -0.53
    avo
    -0.53
    coran
    -0.51
    twimg
    -0.50
    cole
    -0.50
    ativis
    -0.49
     Kne
    -0.49
    Kne
    -0.49
    opre
    -0.48
    POSITIVE LOGITS
     useState
    3.19
    useState
    2.83
     AssemblyCulture
    0.97
     useRef
    0.84
    MigrationBuilder
    0.80
    Przypisy
    0.76
     StatefulWidget
    0.75
     useEffect
    0.74
    ︎
    0.72
     ModelExpression
    0.70
    Activations Density 0.015%

    No Known Activations