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. 21-GEMMASCOPE-RES-16K
    6. 2410
    Prev
    Next
    INDEX
    Explanations

    references to restorative or recovery concepts in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.99
     ivelany
    -0.89
     كومونز
    -0.84
    ByDefault
    -0.79
     "..\..\
    -0.79
     "..\..\..\
    -0.77
     Wikimedijinoj
    -0.76
    Chham
    -0.76
     Walkover
    -0.76
    ItemBackground
    -0.75
    POSITIVE LOGITS
     assured
    0.75
    rest
    0.70
     rest
    0.70
    Rest
    0.69
     REST
    0.67
     Rest
    0.66
    orer
    0.58
    REST
    0.57
    assured
    0.55
    uar
    0.49
    Activations Density 0.058%

    No Known Activations