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. 3-GEMMASCOPE-RES-16K
    6. 12714
    Prev
    Next
    INDEX
    Explanations

    sequences or instructions involving steps or actions in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     électroniques
    -0.50
     kullanılan
    -0.49
     przecież
    -0.46
     aload
    -0.44
     grown
    -0.43
     Tienen
    -0.42
    toBe
    -0.42
     moteurs
    -0.42
     élect
    -0.41
    ydı
    -0.41
    POSITIVE LOGITS
     Audiodateien
    0.93
     ostavi
    0.85
     ModelExpression
    0.83
    TagMode
    0.82
     EconPapers
    0.81
    SharedDtor
    0.81
     تكبرها
    0.79
    httphttps
    0.77
    WebVitals
    0.76
    évaluateur
    0.76
    Activations Density 0.563%

    No Known Activations