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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 20
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createClass
    -0.63
     doInBackground
    -0.61
     azar
    -0.59
     Aitken
    -0.59
    intele
    -0.52
     tinh
    -0.52
    **********/
    -0.51
    Initializable
    -0.51
     onData
    -0.51
     rub
    -0.50
    POSITIVE LOGITS
     horizontal
    0.68
     vertical
    0.67
     Horizontal
    0.63
    DockStyle
    0.61
    ままで
    0.58
     staple
    0.58
    Horizontal
    0.57
    izontal
    0.57
    ConstraintMaker
    0.56
     horizontally
    0.56
    Activations Density 2.437%

    No Known Activations