© 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. 24-GEMMASCOPE-RES-16K
    11. 10206
    Prev
    Next
    INDEX
    Explanations

    issues related to environmental standards and regulations

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

    Preceding words indicate a state or condition

    np_acts-logits-general · gemini-2.0-flash

    legal and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonsoft
    -0.69
    GOTREF
    -0.69
     Cæsar
    -0.65
    ྑ
    -0.62
    signable
    -0.54
     transférez
    -0.53
     initComponents
    -0.52
    Castle
    -0.52
    isissez
    -0.52
    collage
    -0.51
    POSITIVE LOGITS
     وأن
    0.48
    NameInMap
    0.37
    verwijspagina
    0.36
     ""],
    0.33
    TestingModule
    0.33
     ""))
    0.32
    tinyos
    0.32
    UniformLocation
    0.30
    endpush
    0.29
    省市镇
    0.29
    Activations Density 0.974%

    No Known Activations