© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7451
    Prev
    Next
    INDEX
    Explanations

    conversations or interactions surrounding individuals, particularly in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adó
    -0.32
    滋味
    -0.30
    transQ
    -0.28
    不定
    -0.28
    Unmanaged
    -0.27
     wiedzy
    -0.27
    Access
    -0.27
     Quiero
    -0.26
    Биография
    -0.26
    🌽
    -0.26
    POSITIVE LOGITS
     saw
    0.73
    saw
    0.69
     sees
    0.65
     seeing
    0.63
     WebDriverWait
    0.62
     see
    0.61
    Personensuche
    0.58
    +#+
    0.57
     BoxFit
    0.56
    Saw
    0.55
    Activations Density 0.260%

    No Known Activations