© 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. 7-GEMMASCOPE-RES-16K
    11. 15468
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific or botanical classification and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -2.28
    ekš
    -0.62
    yszer
    -0.60
    vény
    -0.60
     שח
    -0.59
    himo
    -0.58
    pośred
    -0.57
    çası
    -0.57
    してみて
    -0.57
    Kont
    -0.56
    POSITIVE LOGITS
    sweise
    0.84
    ième
    0.81
    zelfde
    0.80
    iyle
    0.72
     يتيمه
    0.68
     zijne
    0.68
    یان
    0.65
    یتی
    0.65
    ی
    0.64
     miniaturka
    0.62
    Activations Density 5.600%

    No Known Activations