© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7954
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal definitions and criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by articles or "part"

    np_acts-logits-general · gemini-2.0-flash

    not constitute or qualify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.49
    原始内容存档于
    -0.34
    WriteBarrier
    -0.33
     بص
    -0.31
     ioutil
    -0.30
     protoimpl
    -0.29
    erring
    -0.29
    ([
    -0.28
    jauh
    -0.28
    webElementXpaths
    -0.28
    POSITIVE LOGITS
    立派
    0.69
     незавершена
    0.65
     válido
    0.64
    ConstraintMaker
    0.61
     valid
    0.60
     miniaturka
    0.59
     transfieras
    0.59
     namanya
    0.58
     legitimate
    0.57
     válida
    0.56
    Activations Density 0.752%

    No Known Activations