Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 13609
    Prev
    Next
    INDEX
    Explanations

    terms and components related to web applications and server configurations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.56
    setVerticalGroup
    -0.51
    fileID
    -0.49
     par
    -0.47
    getHeaders
    -0.47
     gibi
    -0.46
    プション
    -0.46
    fruta
    -0.45
     Grange
    -0.44
    ండ
    -0.43
    POSITIVE LOGITS
    WebServlet
    1.25
    WebControls
    1.23
    djangoproject
    1.23
     servlet
    1.04
     Servlet
    1.02
     HttpServlet
    0.98
    BASEPATH
    0.95
    WSGI
    0.93
     pleaſure
    0.91
     JSP
    0.90
    Activations Density 0.338%

    No Known Activations