© 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. 12-GEMMASCOPE-RES-16K
    6. 9302
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and references related to algebraic geometry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rumi
    -0.32
    WebElementEntity
    -0.31
     Mahal
    -0.30
     Tread
    -0.29
     aseg
    -0.29
    complexType
    -0.28
    تفصیلات
    -0.28
    BufferException
    -0.28
     آرام
    -0.28
     Whites
    -0.27
    POSITIVE LOGITS
    ponses
    0.67
     Verſ
    0.56
     ſche
    0.55
    뀜
    0.54
     referenties
    0.54
     COUNTER
    0.54
     вікісторінку
    0.53
     indígen
    0.52
     queſta
    0.52
    Naissance
    0.52
    Activations Density 2.403%

    No Known Activations