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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 10540
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and engineering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.96
     queſta
    -0.93
     Infórmanos
    -0.91
    
    -0.90
     للاسماء
    -0.90
    帖最后由
    -0.83
     AssemblyCompany
    -0.83
     otomatig
    -0.81
     المعيارى
    -0.79
     فريبيس
    -0.78
    POSITIVE LOGITS
    rid
    0.34
     rid
    0.32
     inf
    0.30
     mus
    0.30
     stab
    0.29
     (
    0.29
     official
    0.29
     pret
    0.29
     pres
    0.28
     cre
    0.28
    Activations Density 0.557%

    No Known Activations