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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 9503
    Prev
    Next
    INDEX
    Explanations

    references to scientific or technical terminologies related to data, machinery, and computations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.54
    makeText
    -0.54
     betweenstory
    -0.54
     iprot
    -0.50
    strument
    -0.50
    MigrationBuilder
    -0.48
    MemoryWarning
    -0.47
     membran
    -0.47
    ScopeManager
    -0.47
    اریخ
    -0.47
    POSITIVE LOGITS
     الحره
    0.67
    发表于
    0.56
     Allociné
    0.56
    seitigen
    0.54
    förder
    0.53
    🏻‍♀️
    0.53
    warded
    0.53
     åren
    0.52
    seitige
    0.52
     convertView
    0.51
    Activations Density 0.685%

    No Known Activations