© 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. 10-GEMMASCOPE-RES-16K
    6. 11928
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and criminal cases, particularly involving public figures and allegations of wrongdoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eins
    -0.42
     present
    -0.38
     my
    -0.38
     none
    -0.36
     rabat
    -0.32
    CreateMap
    -0.30
    adalajara
    -0.30
     nor
    -0.30
     open
    -0.29
     hal
    -0.29
    POSITIVE LOGITS
    OGND
    0.82
     GenerationType
    0.76
     Wicidata
    0.72
     متعلقه
    0.71
     utafitiHapana
    0.70
     المعيارى
    0.70
    IntoConstraints
    0.69
    ⮕
    0.67
    OCCURRED
    0.67
     '\\;'
    0.67
    Activations Density 1.467%

    No Known Activations