© 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. 31-GEMMASCOPE-RES-16K
    11. 5533
    Prev
    Next
    INDEX
    Explanations

    phrases related to corporate and business affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    company names and financial/conflicts of interest disclosures.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hjemmeside
    -0.56
     utilidad
    -0.53
     inspección
    -0.53
     provecho
    -0.51
     electricidad
    -0.50
    plaatst
    -0.50
     Turquía
    -0.49
     planificación
    -0.49
     senderismo
    -0.49
     prácti
    -0.49
    POSITIVE LOGITS
     Samsung
    0.89
     Sony
    0.85
     Pfizer
    0.81
     IBM
    0.81
     Nike
    0.81
     Coca
    0.80
     Microsoft
    0.79
     Mitsubishi
    0.79
     Siemens
    0.78
     Nestlé
    0.76
    Activations Density 2.435%

    No Known Activations