© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7047
    Prev
    Next
    INDEX
    Explanations

    references to bridges or related concepts

    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
     shifting
    -0.28
    permute
    -0.26
     barata
    -0.25
    d
    -0.25
    setProperty
    -0.25
     química
    -0.24
    setFile
    -0.24
     certain
    -0.24
    printStats
    -0.24
     kimia
    -0.24
    POSITIVE LOGITS
     propOrder
    0.93
    SequentialGroup
    0.87
    GEBURTSDATUM
    0.84
    ########.
    0.80
     виправивши
    0.79
    parsedMessage
    0.75
    Bridge
    0.75
    Brid
    0.74
     Brid
    0.72
    brid
    0.72
    Activations Density 0.184%

    No Known Activations