© 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-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 8511
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or ongoing processes

    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
     kaarangay
    -0.63
     Италијани
    -0.62
    oa̍t
    -0.60
    iſen
    -0.60
    roën
    -0.58
     AssemblyVersion
    -0.54
     Roskov
    -0.54
     EconPapers
    -0.54
    Obrázky
    -0.53
    qrst
    -0.52
    POSITIVE LOGITS
     myös
    0.46
     Also
    0.44
     also
    0.44
     ayrıca
    0.42
     Também
    0.42
    also
    0.42
     también
    0.41
    Also
    0.40
     även
    0.39
     também
    0.39
    Activations Density 1.644%

    No Known Activations