© 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. 30-GEMMASCOPE-RES-16K
    11. 9981
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries often related to technology and programming

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

    Following certain conjunctions or relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    removing spam, viruses, and credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.55
     Italij
    -0.49
    esModule
    -0.49
     tričko
    -0.45
     Keuangan
    -0.44
     podjet
    -0.44
    djangoproject
    -0.43
     financiero
    -0.42
     Könige
    -0.42
     temporadas
    -0.42
    POSITIVE LOGITS
    artificial
    0.65
     Automated
    0.59
    satellite
    0.58
     artificial
    0.57
     Virtual
    0.56
    automated
    0.56
     SAC
    0.56
     Artificial
    0.55
     automated
    0.55
     Farm
    0.54
    Activations Density 2.513%

    No Known Activations