© 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. 28-GEMMASCOPE-RES-16K
    11. 11001
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation and injury in a legal context

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

    "arises," "arose," or "arising" after an injury

    np_acts-logits-general · gemini-2.0-flash

    arose out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isContained
    -0.60
    Jîn
    -0.54
    LayoutStyle
    -0.51
    comuna
    -0.45
    
    -0.43
     للمعارف
    -0.42
    BeforeAll
    -0.42
    новниш
    -0.42
     Administrativna
    -0.42
     FBref
    -0.42
    POSITIVE LOGITS
    (!)
    0.56
     (!)
    0.54
     MainAxisSize
    0.52
     rather
    0.50
     AssemblyCompany
    0.47
    íncia
    0.46
    rather
    0.44
     (=
    0.43
     Rather
    0.43
     (“
    0.43
    Activations Density 1.227%

    No Known Activations