© 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 EvalsExportsinterp-engineNEWAPI 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. 7781
    Prev
    Next
    INDEX
    Explanations

    phrases that relate to copyright and usage permissions in software licensing

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

    Follows "copyright" or similar legal terms

    np_acts-logits-general · gemini-2.0-flash

    copyright notices and branding

    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
     المعيارى
    -0.36
     snak
    -0.35
    INGTON
    -0.32
    enumii
    -0.32
     Halloween
    -0.30
     triển
    -0.30
    čilo
    -0.30
     Colombie
    -0.30
     livet
    -0.30
     cabbage
    -0.30
    POSITIVE LOGITS
     AssemblyCompany
    1.16
     branding
    0.91
     logo
    0.89
    logo
    0.89
     logos
    0.88
    Logo
    0.84
     Logo
    0.82
    branding
    0.82
     Branding
    0.81
    Branding
    0.77
    Activations Density 0.279%

    No Known Activations