© 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. 12-GEMMASCOPE-RES-16K
    11. 5227
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or transformation of movements and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -0.51
     насељу
    -0.48
     eyel
    -0.45
    HXLINE
    -0.44
     kife
    -0.43
     chande
    -0.43
    請繼續往下閱讀
    -0.43
    qtype
    -0.43
    separ
    -0.41
    Ҭ
    -0.41
    POSITIVE LOGITS
    featureID
    0.49
    numerusform
    0.47
     PeEnEo
    0.38
     ursprünglich
    0.38
     превра
    0.37
     pinulongan
    0.36
     schein
    0.36
    endorong
    0.35
     seemingly
    0.35
     trajets
    0.35
    Activations Density 0.734%

    No Known Activations