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. 0-GEMMASCOPE-RES-16K
    6. 311
    Prev
    Next
    INDEX
    Explanations

    terms related to finality or completion in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.63
     StatelessWidget
    -0.61
    Transcripción
    -0.59
    BeginContext
    -0.58
    
    -0.55
     WebDriverWait
    -0.55
    QMetaType
    -0.55
    pushd
    -0.54
    classnames
    -0.53
     defaultstate
    -0.53
    POSITIVE LOGITS
     final
    3.44
    final
    3.05
    Final
    2.85
     Final
    2.83
     FINAL
    2.72
    FINAL
    2.54
     finale
    2.16
    最后
    1.90
     finals
    1.88
     finally
    1.84
    Activations Density 0.121%

    No Known Activations