© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122106
    Prev
    Next
    INDEX
    Explanations

    references to public and private sectors, particularly in the context of education and funding

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

    public domain or common good

    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-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
     irmã
    -0.52
     Lengkap
    -0.51
     Económica
    -0.49
     Técnica
    -0.44
     Milán
    -0.43
     boneca
    -0.42
     vuelo
    -0.41
     Turquía
    -0.41
     Tecnología
    -0.41
     rencontr
    -0.41
    POSITIVE LOGITS
     public
    1.05
     Public
    0.94
    Public
    0.88
     publique
    0.77
     PUBLIC
    0.75
     publick
    0.72
     pública
    0.71
     publics
    0.70
    公共
    0.69
     púb
    0.69
    Activations Density 0.018%

    No Known Activations