© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 25-GEMMASCOPE-RES-16K
    11. 16113
    Prev
    Next
    INDEX
    Explanations

    official legal terms and references related to laws, regulations, and legal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.54
     twe
    -0.52
    +:+
    -0.47
    roppo
    -0.47
    RTLD
    -0.47
    VYMaps
    -0.47
    inheit
    -0.46
    arXiv
    -0.46
    UnifiedTopology
    -0.45
    IntoConstraints
    -0.45
    POSITIVE LOGITS
     pursuant
    0.50
    errHandler
    0.39
    oarece
    0.37
    posedge
    0.37
    findpost
    0.36
     Pursuant
    0.36
     Applicability
    0.35
     незавершена
    0.35
     subsequent
    0.35
    rotum
    0.34
    Activations Density 2.210%

    No Known Activations