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. 25-GEMMASCOPE-RES-16K
    6. 5699
    Prev
    Next
    INDEX
    Explanations

    details about software updates and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.74
    出版年
    -0.56
    RectangleBorder
    -0.56
    lgari
    -0.56
    ContentAsync
    -0.54
    ThroughAttribute
    -0.53
    ///</
    -0.51
    MLLoader
    -0.50
    glBegin
    -0.50
    HasForeignKey
    -0.50
    POSITIVE LOGITS
     Added
    1.08
     Fixes
    1.07
     fixes
    1.06
     Fix
    1.03
    Added
    1.01
     fix
    0.99
    Fix
    0.97
     Improvements
    0.93
     Fixed
    0.93
     Improved
    0.91
    Activations Density 0.488%

    No Known Activations