© 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. 2-GEMMASCOPE-RES-16K
    11. 4404
    Prev
    Next
    INDEX
    Explanations

    words related to names, particularly those of people and works of art

    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
    tagHelperRunner
    -0.51
    Diweddarwch
    -0.44
     Tyrol
    -0.41
    TokenNameLBRACE
    -0.38
    Bezier
    -0.38
     AGA
    -0.37
     REM
    -0.37
     intptr
    -0.37
     triplets
    -0.37
    stang
    -0.36
    POSITIVE LOGITS
     esp
    0.61
    é
    0.60
    ee
    0.53
     broker
    0.53
     fe
    0.52
    ea
    0.51
    ي
    0.50
    esp
    0.48
     []).
    0.47
    פ
    0.47
    Activations Density 0.665%

    No Known Activations