© 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. 11695
    Prev
    Next
    INDEX
    Explanations

    specific references to holes and their contexts in various subjects

    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
    principalTable
    -0.56
    stylers
    -0.48
    Scalars
    -0.47
     juſ
    -0.44
    AnchorTagHelper
    -0.43
     beſ
    -0.42
    ciamento
    -0.41
     cuarzo
    -0.41
     ſal
    -0.41
     Upland
    -0.41
    POSITIVE LOGITS
     holes
    2.81
     hole
    2.78
     Hole
    2.33
    holes
    2.27
    hole
    2.27
     Holes
    2.22
    Hole
    2.19
     HOLE
    2.17
    Holes
    2.14
    HOLE
    1.88
    Activations Density 0.959%

    No Known Activations