© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Apple" and variations of it, including homophones and related words

    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
    ness
    -0.56
    으로
    -0.49
    ів
    -0.49
    n
    -0.46
    ers
    -0.45
    not
    -0.43
    н
    -0.43
     utafitiHapana
    -0.41
    non
    -0.40
    north
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.65
    AutoresizingMask
    0.53
     Wiktionnaire
    0.52
    सनीय
    0.50
    idoscope
    0.50
    ttes
    0.49
    mente
    0.49
    ctomy
    0.46
    e
    0.45
    RenderAtEndOf
    0.45
    Activations Density 0.341%

    No Known Activations