© 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. 23-GEMMASCOPE-RES-16K
    11. 9175
    Prev
    Next
    INDEX
    Explanations

    mathematical results and definitions related to lemma and theorem statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.52
    windowFixed
    -0.50
    ieteur
    -0.47
     Shaw
    -0.45
     pageSize
    -0.45
    PropertyChanging
    -0.44
     Hall
    -0.42
     SHAW
    -0.41
     Adria
    -0.41
     stör
    -0.41
    POSITIVE LOGITS
    kloped
    0.42
    RegressionTest
    0.40
     folgender
    0.38
    MethodManager
    0.36
     verw
    0.33
     conséquence
    0.33
    Practi
    0.33
     tartalomajánló
    0.33
    solicited
    0.33
    utivo
    0.33
    Activations Density 0.764%

    No Known Activations