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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12652
    Prev
    Next
    INDEX
    Explanations

    technical terms and configurations related to computing

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

    Instructions for creating or modifying

    np_acts-logits-general · gemini-2.0-flash

    create and set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.73
     />);
    -0.58
     JScrollPane
    -0.55
    ModelAndView
    -0.55
    getSystemService
    -0.53
    ruptedException
    -0.53
    onResume
    -0.52
    CURSOR
    -0.52
     QWidget
    -0.52
     columnIndex
    -0.51
    POSITIVE LOGITS
     assign
    0.67
     assigned
    0.67
     created
    0.66
     assigning
    0.65
     create
    0.58
    atég
    0.54
     Assign
    0.53
     asig
    0.52
     copied
    0.52
     créer
    0.52
    Activations Density 0.832%

    No Known Activations