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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3228
    Prev
    Next
    INDEX
    Explanations

    phrases related to learning outcomes and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "from"

    np_acts-logits-general · gemini-2.0-flash

    learn objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    
    -0.67
     SafeMath
    -0.58
     Wikimedijinoj
    -0.58
    issors
    -0.54
    jectures
    -0.52
    oredCriteria
    -0.51
     queſta
    -0.50
     الرياضيه
    -0.50
    urities
    -0.50
    trus
    -0.50
    POSITIVE LOGITS
     ✭✭
    0.41
     understanding
    0.40
    mahaman
    0.36
    <%@
    0.34
    yntaxException
    0.34
     gelernt
    0.34
    invokeLater
    0.33
     knowledge
    0.33
     leren
    0.32
     lleg
    0.32
    Activations Density 0.288%

    No Known Activations