Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7640
    Prev
    Next
    INDEX
    Explanations

    mentions of academic institutions and significant achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.64
     torchvision
    -0.54
    onoi
    -0.54
    сылкі
    -0.54
     @"/
    -0.54
    getitem
    -0.51
     Obrador
    -0.51
     Moonlight
    -0.51
    Handlung
    -0.51
     risk
    -0.51
    POSITIVE LOGITS
     Kampala
    0.94
     Ugandan
    0.86
     Uganda
    0.80
    Uganda
    0.69
     AssemblyTitle
    0.68
     Bogotá
    0.66
    /*
    0.64
    DIPSETTING
    0.62
     Ghent
    0.61
     Cartagena
    0.61
    Activations Density 0.183%

    No Known Activations