© 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. 14676
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and legal proceedings

    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
     ent
    -0.40
     RouterModule
    -0.40
     &___
    -0.39
    CppCodeGen
    -0.37
     AssemblyCompany
    -0.36
     архивлан
    -0.36
     Ruhr
    -0.35
    oneofs
    -0.35
    sanitize
    -0.35
     arms
    -0.33
    POSITIVE LOGITS
     Austin
    0.88
    Austin
    0.84
     AUSTIN
    0.72
     austin
    0.65
    austin
    0.61
     ATX
    0.60
     Aust
    0.57
    ATX
    0.56
     Statesman
    0.53
     Travis
    0.52
    Activations Density 0.230%

    No Known Activations