© 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. 39-GEMMASCOPE-RES-16K
    6. 300
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and variables within statistical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inalámbrica
    -0.44
     invitados
    -0.43
     p
    -0.43
     m
    -0.42
     negociaciones
    -0.41
     g
    -0.40
     q
    -0.40
     diputados
    -0.40
     pecados
    -0.40
     plásticos
    -0.40
    POSITIVE LOGITS
    出版年
    0.72
    MLLoader
    0.68
     queſta
    0.68
     ProtoMessage
    0.59
     Ê
    0.59
     يتيمه
    0.59
     مشين
    0.59
    הערות
    0.59
    posedge
    0.58
     HasFactory
    0.57
    Activations Density 1.050%

    No Known Activations