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. 8266
    Prev
    Next
    INDEX
    Explanations

    specific biochemical processes or terms related to research on Sierpiński gaskets and other mathematical constructs

    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
     FormBuilder
    -0.72
    :].
    -0.72
    +:+
    -0.69
    şil
    -0.66
    consulté
    -0.65
     kiệm
    -0.63
     []:
    -0.63
    icordia
    -0.61
     Ste
    -0.60
     Fe
    -0.60
    POSITIVE LOGITS
    abestanden
    0.79
    Kanpo
    0.75
     accompag
    0.72
     Vaugh
    0.68
     lccn
    0.67
    Viited
    0.67
     kön
    0.67
     Baillargeon
    0.66
     attaché
    0.66
    örté
    0.66
    Activations Density 0.575%

    No Known Activations