© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 10533
    Prev
    Next
    INDEX
    Explanations

    terminologies related to legal and regulatory compliance issues

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

    lack of control or strictness

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects words and phrases signaling risk, danger, safety failures, or ignored warnings.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    pDialog
    -0.50
    GOTREF
    -0.46
    最快更新
    -0.46
    SizeMode
    -0.44
     disambiguazione
    -0.41
    Bioaccumulative
    -0.41
     يتيمه
    -0.41
    Hentet
    -0.40
     Musa
    -0.40
    overlay
    -0.40
    POSITIVE LOGITS
     carelessness
    0.47
     peggio
    0.43
     peligroso
    0.43
    SequentialGroup
    0.42
    ophosph
    0.42
     lax
    0.42
     permis
    0.42
     loophole
    0.41
     careless
    0.41
     defaultstate
    0.40
    Activations Density 0.103%

    No Known Activations