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. 11599
    Prev
    Next
    INDEX
    Explanations

    quantitative financial and statistical data related to income and measurements

    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
    ScopeManager
    -0.64
    ⓧ
    -0.59
    GetAsync
    -0.56
     للمعارف
    -0.56
    EditorBrowsable
    -0.53
    )$_
    -0.51
    elemField
    -0.50
    zzleHttp
    -0.50
     فريبيس
    -0.48
    mpia
    -0.46
    POSITIVE LOGITS
     chrétien
    0.79
    aarrggbb
    0.79
     religieuses
    0.76
    HasAnnotation
    0.75
     étoit
    0.74
     foncé
    0.73
     ainfi
    0.73
     chré
    0.72
     avoient
    0.70
     zelve
    0.70
    Activations Density 0.966%

    No Known Activations