© 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-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12218
    Prev
    Next
    INDEX
    Explanations

    programming constructs and operations related to lists and object-oriented structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.57
    Atoi
    -0.39
    ној
    -0.39
    Itoa
    -0.38
    reuth
    -0.38
    catraz
    -0.36
    etate
    -0.35
    겜
    -0.34
    襬
    -0.32
    ﷺ
    -0.31
    POSITIVE LOGITS
     double
    3.53
    double
    3.06
     Double
    2.98
     doubles
    2.78
    Double
    2.75
     DOUBLE
    2.75
     doble
    2.67
     doubled
    2.56
    DOUBLE
    2.44
     dobles
    2.42
    Activations Density 0.797%

    No Known Activations