© 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. 19-GEMMASCOPE-RES-16K
    11. 6704
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers, particularly those that may relate to characters or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    u
    -0.64
     relative
    -0.58
    stock
    -0.49
    an
    -0.49
    relative
    -0.47
    onucleotide
    -0.45
    logenetic
    -0.45
    coming
    -0.44
     fide
    -0.43
    μβ
    -0.43
    POSITIVE LOGITS
    SBATCH
    0.80
    MLLoader
    0.76
     Mij
    0.73
    ьаж
    0.69
     lij
    0.67
    hej
    0.67
    ništ
    0.66
    edrez
    0.65
    fjspx
    0.65
    новниш
    0.65
    Activations Density 0.181%

    No Known Activations