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. 9000
    Prev
    Next
    INDEX
    Explanations

    occurrences of asterisks

    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
    Revenir
    -0.56
     муніципалі
    -0.53
     
    -0.49
     Audiodateien
    -0.45
     Oester
    -0.42
     E
    -0.41
    ZER
    -0.40
     Clear
    -0.39
     maaf
    -0.39
     copas
    -0.38
    POSITIVE LOGITS
    Parcelize
    1.09
     referenties
    0.92
    WithIOException
    0.91
     (*(
    0.87
    WebVitals
    0.86
     StatefulWidget
    0.86
    TagMode
    0.86
    basicConfig
    0.85
     TestBed
    0.81
     GenerationType
    0.79
    Activations Density 0.386%

    No Known Activations