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. 6099
    Prev
    Next
    INDEX
    Explanations

    examples that illustrate general concepts or principles, often using a specific context or situation

    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
     itſelf
    -1.12
    دانشنامهٔ
    -1.05
     Houſe
    -1.01
     Diſ
    -1.00
     propOrder
    -0.99
     Anſ
    -0.99
    addCriterion
    -0.99
     Monfieur
    -0.99
     Efq
    -0.98
     Reſ
    -0.97
    POSITIVE LOGITS
     example
    0.88
     exemple
    0.74
    example
    0.72
     Example
    0.71
     "
    0.68
     Beispiel
    0.66
     například
    0.66
     examples
    0.64
     esempio
    0.64
     exempel
    0.64
    Activations Density 0.152%

    No Known Activations