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. 8689
    Prev
    Next
    INDEX
    Explanations

    elements related to organization, customer satisfaction, and effective communication

    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
    CloseOperation
    -0.57
     AttributeSet
    -0.56
    stdafx
    -0.55
     ExecuteAsync
    -0.53
    شو
    -0.51
    RetentionPolicy
    -0.50
     /\.(
    -0.49
    Xaml
    -0.48
     suf
    -0.47
     Street
    -0.46
    POSITIVE LOGITS
    følgelig
    0.80
     '\\;'
    0.71
     estekak
    0.70
    niająca
    0.69
     مفص
    0.67
     تضيفلها
    0.65
     HasFactory
    0.62
    bcryptjs
    0.59
    writeFieldEnd
    0.58
    EDEFAULT
    0.55
    Activations Density 0.605%

    No Known Activations