© 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. 14582
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations of concepts related to legal and medical terminology

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

    Definition or classification

    np_acts-logits-general · gemini-2.0-flash

    what constitutes or violates

    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
    __":
    -0.43
    DockStyle
    -0.41
    InjectAttribute
    -0.40
    ofire
    -0.36
    PageFactory
    -0.36
    XDECREF
    -0.35
    FieldOffsetTable
    -0.35
    autant
    -0.35
    WaitGroup
    -0.34
    eron
    -0.34
    POSITIVE LOGITS
     qualifies
    1.35
     classed
    1.30
     classify
    1.23
     classified
    1.22
     qualify
    1.15
     considered
    1.14
     Considered
    1.08
     classi
    1.06
     classifying
    1.05
    属于
    1.03
    Activations Density 1.157%

    No Known Activations