© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15202
    Prev
    Next
    INDEX
    Explanations

    various types of filters used in data processing or analysis contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newState
    -0.48
     newName
    -0.43
    期刊论文
    -0.41
     Randy
    -0.41
     McCabe
    -0.41
     Lande
    -0.41
     Mont
    -0.41
    knecht
    -0.41
     Zwe
    -0.39
     Boyce
    -0.39
    POSITIVE LOGITS
     filter
    3.59
     filters
    3.45
     Filter
    3.33
     Filters
    3.20
     filtering
    3.09
     FILTER
    3.05
    Filter
    2.97
    filter
    2.92
    filters
    2.92
     filtered
    2.84
    Activations Density 0.165%

    No Known Activations