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. 13-GEMMASCOPE-RES-16K
    6. 10945
    Prev
    Next
    INDEX
    Explanations

    specific entities or objects related to various contexts, particularly focusing on products and interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.59
    toHaveBeenCalled
    -0.53
    printStackTrace
    -0.52
    oureux
    -0.52
    httphttps
    -0.50
    inars
    -0.50
    ziału
    -0.49
    awtextra
    -0.49
     Basta
    -0.49
    hitheater
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    0.54
    ̍t
    0.52
    égard
    0.51
    ="@+
    0.51
     باخ
    0.49
     ويكي
    0.49
    ыр
    0.49
     فريبيس
    0.48
     MOBILE
    0.48
     Candidate
    0.47
    Activations Density 0.617%

    No Known Activations