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. 10-GEMMASCOPE-RES-16K
    6. 13170
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly in the context of sports or personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -1.15
    ViewFeatures
    -0.95
    \{\\
    -0.93
     الحره
    -0.89
    DockStyle
    -0.85
     المعيارى
    -0.84
     saites
    -0.82
     iconLine
    -0.82
    migrationBuilder
    -0.80
     AspNetCore
    -0.80
    POSITIVE LOGITS
    TestingModule
    0.52
     caccia
    0.50
    pe
    0.49
     etmeye
    0.49
     deose
    0.48
     outono
    0.47
     figliu
    0.47
     jeito
    0.47
     istrinya
    0.47
     montagna
    0.47
    Activations Density 0.749%

    No Known Activations