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. 6838
    Prev
    Next
    INDEX
    Explanations

    technical terms, especially related to programming and legal 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
     ddelweddau
    -0.47
    hängig
    -0.46
     ***!
    -0.45
     footage
    -0.45
     Dickerson
    -0.44
     Ra
    -0.44
     للاسماء
    -0.43
     überlegen
    -0.43
     Noyes
    -0.43
    opher
    -0.42
    POSITIVE LOGITS
     Geraadpleegd
    0.76
     CURIAM
    0.71
    Portale
    0.70
     înc
    0.69
    EndInit
    0.67
    usercontent
    0.66
     CascadeType
    0.65
    InjectMocks
    0.64
    AndEndTag
    0.64
     MainAxisSize
    0.64
    Activations Density 2.437%

    No Known Activations