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. 11-GEMMASCOPE-RES-16K
    6. 7988
    Prev
    Next
    INDEX
    Explanations

    terms and references related to mathematics and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------
    -1.06
     Jefus
    -0.95
     myſelf
    -0.95
     themſelves
    -0.92
    }>;
    -0.91
    ContentAsync
    -0.89
    JsonPropertyName
    -0.88
     Cuckoo
    -0.88
     verily
    -0.88
     becauſe
    -0.87
    POSITIVE LOGITS
     Mathis
    1.48
     MATH
    1.35
     Math
    1.33
    math
    1.27
    Math
    1.22
     math
    1.21
    MATH
    1.18
     Mathilde
    0.98
     Mathi
    0.92
    ATH
    0.83
    Activations Density 0.139%

    No Known Activations