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. 13795
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and decisions

    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
     WebDriverWait
    -0.59
    pédie
    -0.58
    '}>
    -0.54
    ')")
    -0.53
    annica
    -0.53
    WithMany
    -0.52
    BufferException
    -0.52
    avits
    -0.51
    τιά
    -0.50
    riet
    -0.50
    POSITIVE LOGITS
    Similar
    0.95
     similar
    0.91
     SIMILAR
    0.89
    similar
    0.85
     Similar
    0.84
     hason
    0.80
     ähnlich
    0.78
     similaire
    0.72
     analogous
    0.72
     ähnliche
    0.72
    Activations Density 0.458%

    No Known Activations