© 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. 3990
    Prev
    Next
    INDEX
    Explanations

    information related to evidence, findings, and documentation in various contexts

    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
    
    -0.95
     esetén
    -0.92
    GEBURTSDATUM
    -0.78
     дописавши
    -0.76
     ujednoznacz
    -0.73
    Hentet
    -0.72
     виправивши
    -0.71
    請繼續往下閱讀
    -0.70
    UserScript
    -0.66
     snippetHide
    -0.64
    POSITIVE LOGITS
     itself
    0.63
    ollectionView
    0.56
    iest
    0.55
     useHistory
    0.55
    aarrggbb
    0.55
    iniest
    0.53
    mPaint
    0.53
    InvalidProtocol
    0.51
    PropertyChanging
    0.51
     onBind
    0.51
    Activations Density 3.162%

    No Known Activations