© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11626
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions and attributes related to physical properties and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.69
     resourceCulture
    -0.68
     estekak
    -0.63
     <<<<<<<<<<<<<<
    -0.59
     MessageBoxIcon
    -0.58
    ModelForm
    -0.57
    migrationBuilder
    -0.57
    MLLoader
    -0.56
     autorytatywna
    -0.54
    __":
    -0.54
    POSITIVE LOGITS
     makes
    1.08
     membuatnya
    1.05
     ensures
    1.04
     means
    0.97
     ensured
    0.96
    使得
    0.93
    使其
    0.93
     menjadikan
    0.89
     renders
    0.88
     делает
    0.88
    Activations Density 1.111%

    No Known Activations