© 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. 40-GEMMASCOPE-RES-16K
    6. 6279
    Prev
    Next
    INDEX
    Explanations

    variants and conjugations of the term "obstruction" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.59
    WireFormatLite
    -0.49
     esternos
    -0.49
     kaarangay
    -0.48
    thâu
    -0.47
    IUrlHelper
    -0.47
    ValueStyle
    -0.46
     EconPapers
    -0.46
    SharedCtor
    -0.46
    AutoScale
    -0.45
    POSITIVE LOGITS
     Walkover
    0.43
     served
    0.43
    最快更新
    0.39
    iously
    0.36
     conserv
    0.35
     ALONE
    0.35
    enderror
    0.35
    NOX
    0.35
    ously
    0.34
    Filmografie
    0.34
    Activations Density 0.315%

    No Known Activations