© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15077
    Prev
    Next
    INDEX
    Explanations

    relationships and contrasts between concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sær
    -0.53
    enumi
    -0.49
    不止
    -0.48
    以外にも
    -0.47
    olm
    -0.46
     nejen
    -0.46
    antwo
    -0.45
     verschiedener
    -0.45
     Apakah
    -0.44
    %=
    -0.43
    POSITIVE LOGITS
     Conversely
    1.87
     conversely
    1.85
    Conversely
    1.78
     meanwhile
    1.62
     Whereas
    1.53
    Whereas
    1.52
     Meanwhile
    1.51
    whereas
    1.50
    Meanwhile
    1.48
     whereas
    1.47
    Activations Density 0.398%

    No Known Activations