© 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. 3-GEMMASCOPE-RES-16K
    6. 9476
    Prev
    Next
    INDEX
    Explanations

    terms related to automatic or automated systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mergeFrom
    -0.45
    řád
    -0.44
    titleMargin
    -0.40
     acá
    -0.38
     onCreateView
    -0.38
    hdashline
    -0.38
    Ƚ
    -0.37
     Berlín
    -0.37
    ślę
    -0.36
    iettivo
    -0.36
    POSITIVE LOGITS
     automatic
    3.83
    automatic
    3.50
     Automatic
    3.47
    Automatic
    3.45
     automat
    3.13
     AUTOMATIC
    3.05
     automatically
    2.92
     automated
    2.91
     автомати
    2.83
     automatique
    2.73
    Activations Density 0.145%

    No Known Activations