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. 15221
    Prev
    Next
    INDEX
    Explanations

    procedures and steps related to cooking or kitchen tasks

    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
    yntaxException
    -0.45
     للمعارف
    -0.42
     mammal
    -0.39
    bys
    -0.39
     efforts
    -0.39
     izan
    -0.38
     attempts
    -0.37
    мен
    -0.37
    seli
    -0.36
     Germain
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.94
    webElementXpaths
    0.87
    Personendaten
    0.82
    LookAnd
    0.78
     برانيه
    0.77
     >=",
    0.75
    featureID
    0.71
    ,:]
    0.70
    "])
    
    0.70
     textStatus
    0.70
    Activations Density 0.424%

    No Known Activations