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. 7-GEMMASCOPE-RES-16K
    6. 8933
    Prev
    Next
    INDEX
    Explanations

    references to user profiles and system-level permissions

    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
    makeText
    -0.59
    
    -0.52
    )}</
    -0.51
    "){
    
    -0.51
     OnInit
    -0.49
    ----</
    -0.49
     فريبيس
    -0.49
    NewGuid
    -0.48
     Alph
    -0.48
    ziplin
    -0.48
    POSITIVE LOGITS
    PhysRevD
    0.63
    DataBinding
    0.62
     fallu
    0.61
    مقاله
    0.60
    Vidite
    0.58
    GOTREF
    0.55
     craindre
    0.54
    Kjelder
    0.53
    emples
    0.52
     recuerdo
    0.51
    Activations Density 0.208%

    No Known Activations