© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7971
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to data structures and processing systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aikaa
    -0.84
     arvio
    -0.66
     valmis
    -0.62
     meille
    -0.62
     jäsen
    -0.60
     vastaan
    -0.60
    ahuje
    -0.59
     avulla
    -0.59
     puol
    -0.59
     mukana
    -0.59
    POSITIVE LOGITS
     تضيفلها
    0.99
    ⓧ
    0.69
     كومونز
    0.67
     nahilalakip
    0.66
    webElementXpaths
    0.61
    reportWebVitals
    0.56
    ########.
    0.53
    tagHelperRunner
    0.52
    ollectionView
    0.52
    liferay
    0.51
    Activations Density 0.767%

    No Known Activations