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. 9-GEMMASCOPE-RES-16K
    6. 9074
    Prev
    Next
    INDEX
    Explanations

    requests for communication or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setPointSize
    -0.56
    كويكب
    -0.54
    CURLOPT
    -0.52
     retirer
    -0.51
     rid
    -0.51
     JPanel
    -0.50
     example
    -0.48
    assertIn
    -0.48
    Newswire
    -0.48
    ConverterFactory
    -0.48
    POSITIVE LOGITS
     بيها
    0.70
     فريبيس
    0.69
    )_/¯
    0.61
    AndEndTag
    0.60
    Einzelnachweise
    0.58
    contact
    0.57
    Contact
    0.56
     Dicapai
    0.56
    تقاوى
    0.54
    oprecipitation
    0.53
    Activations Density 0.098%

    No Known Activations