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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 15101
    Prev
    Next
    INDEX
    Explanations

    software development-related terms, particularly those associated with C/C++ coding and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -1.01
    intellij
    -0.84
    gdx
    -0.73
    $_['
    -0.68
    SBATCH
    -0.67
    apimachinery
    -0.67
    Personendaten
    -0.67
     AssemblyTitle
    -0.65
    Xna
    -0.64
    SourceChecksum
    -0.63
    POSITIVE LOGITS
    RegistryLite
    0.58
     ftate
    0.56
     perfons
    0.54
     fufficient
    0.53
    ſelves
    0.52
     fubject
    0.52
     perſon
    0.51
     ſtate
    0.50
    ſelf
    0.50
     ſeveral
    0.50
    Activations Density 0.222%

    No Known Activations