© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14965
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibility and accountability in actions and their consequences

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

    certainty or control

    np_acts-logits-general · gemini-2.0-flash

    rely on, bear in mind that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stink
    -0.52
     smelly
    -0.49
    ulico
    -0.48
     legit
    -0.48
     stall
    -0.48
     Kah
    -0.47
     stinks
    -0.47
     smell
    -0.47
     smelling
    -0.47
    +#+#
    -0.47
    POSITIVE LOGITS
     beginnetje
    0.63
     ब्रेकडाउन
    0.60
     Chwiliwch
    0.59
    ValueStyle
    0.59
    HasForeignKey
    0.58
     tatuagens
    0.55
     Wiktionnaire
    0.52
     aislado
    0.52
    Portale
    0.49
    出版年
    0.49
    Activations Density 0.818%

    No Known Activations