Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 14279
    Prev
    Next
    INDEX
    Explanations

    references to locations or the presence of something in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monty
    -0.65
     ramo
    -0.65
    dom
    -0.65
    enzo
    -0.63
     Gaff
    -0.62
    epik
    -0.61
    stasia
    -0.61
     ramos
    -0.59
    nbsp
    -0.59
     MacLeod
    -0.59
    POSITIVE LOGITS
     THERE
    1.01
     there
    1.00
    there
    0.95
     frattempo
    0.83
    存于互联网档案馆
    0.81
     CreateTagHelper
    0.81
     berdua
    0.80
     дописавши
    0.79
     Allí
    0.78
     mesmos
    0.78
    Activations Density 0.072%

    No Known Activations