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. 12-GEMMASCOPE-RES-16K
    6. 4430
    Prev
    Next
    INDEX
    Explanations

    code structures related to database entities and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.77
     चीज़ों
    -0.70
    Portály
    -0.60
     MessageBoxIcon
    -0.58
     sist
    -0.58
    LookAnd
    -0.58
     MainAxisSize
    -0.57
    Sprintf
    -0.56
    BagConstraints
    -0.56
    IContainer
    -0.56
    POSITIVE LOGITS
     dég
    0.54
    ItemBackground
    0.53
     skolan
    0.51
    audiovisuel
    0.51
    wolle
    0.50
     urma
    0.50
     épaules
    0.49
     CreateTagHelper
    0.49
     Rothschild
    0.48
     eccell
    0.48
    Activations Density 0.032%

    No Known Activations