© 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. 6567
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated measurements or statistics

    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
    niosek
    -0.45
    rrggbb
    -0.37
     fevere
    -0.37
    MessageTagHelper
    -0.35
    âmetros
    -0.33
     preced
    -0.33
    colhead
    -0.32
     anteced
    -0.32
    ökk
    -0.31
     Too
    -0.31
    POSITIVE LOGITS
    hyrchwyd
    0.67
    protoimpl
    0.67
     AssemblyCulture
    0.60
    rungsseite
    0.56
     resourceCulture
    0.55
     EconPapers
    0.51
    onViewCreated
    0.50
     Paglinawan
    0.48
    TypedDataSet
    0.47
    minecraftforge
    0.46
    Activations Density 0.589%

    No Known Activations