© 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. 25-GEMMASCOPE-RES-16K
    6. 15878
    Prev
    Next
    INDEX
    Explanations

    items related to legal proceedings and court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Volkes
    -0.40
     Kreise
    -0.38
     Gegenteil
    -0.38
     SUBMIT
    -0.36
    BeginInit
    -0.36
    AsUp
    -0.36
    contentLoaded
    -0.36
    StructEnd
    -0.35
    SequentialGroup
    -0.35
     годах
    -0.34
    POSITIVE LOGITS
    ViewFeatures
    0.52
    colnshire
    0.48
     Италијани
    0.47
    hyrchwyd
    0.46
     esternos
    0.45
    Prote
    0.44
     kling
    0.44
    ghalaya
    0.44
    Maur
    0.43
    wrk
    0.42
    Activations Density 0.364%

    No Known Activations