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. 10101
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags

    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
    -0.97
     يتيمه
    -0.84
     nakalista
    -0.83
    Personendaten
    -0.79
    principalColumn
    -0.75
     hiel
    -0.75
    Билгалдахарш
    -0.74
    ViewImports
    -0.74
    énario
    -0.72
    SequentialGroup
    -0.70
    POSITIVE LOGITS
    </
    0.79
     </
    0.76
     "</
    0.75
     '</
    0.65
    ("</
    0.64
    .<
    0.46
    RRect
    0.46
     Kombat
    0.45
    "</
    0.44
    Shaders
    0.44
    Activations Density 0.045%

    No Known Activations