© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1210
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or 'spots' within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    íncia
    -0.75
     Maier
    -0.74
    קישורים
    -0.69
    egis
    -0.67
     Kenner
    -0.66
    ölkerung
    -0.65
    weetened
    -0.64
    Hydra
    -0.64
     Ayres
    -0.64
     مشين
    -0.64
    POSITIVE LOGITS
     spot
    3.58
     Spot
    3.44
    spot
    3.23
    Spot
    3.19
     SPOT
    3.16
     spots
    2.97
     Spots
    2.89
    spots
    2.80
    SPOT
    2.80
    Spots
    2.46
    Activations Density 0.035%

    No Known Activations