© 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. 12344
    Prev
    Next
    INDEX
    Explanations

    specific names and entities related to figures in a historical or political context

    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
    そこは
    -0.46
     tricks
    -0.46
    ぐり
    -0.45
    ншни
    -0.45
    FromNib
    -0.45
    իա
    -0.45
     bowls
    -0.44
    tricks
    -0.43
    tokens
    -0.43
     swaps
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.63
    Rüyada
    0.48
     AssemblyCulture
    0.46
    COUVER
    0.45
    webElementGuid
    0.43
    Insee
    0.43
    oredCriteria
    0.43
    MessageOf
    0.42
    toarele
    0.41
     ComVisible
    0.40
    Activations Density 0.072%

    No Known Activations