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. 13152
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or giving opportunities

    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
     pageable
    -0.46
    fraid
    -0.45
    Pyx
    -0.45
    پیوند
    -0.43
    ConstraintMaker
    -0.42
    nestjs
    -0.40
    el
    -0.40
    none
    -0.40
     réglable
    -0.40
    sdk
    -0.39
    POSITIVE LOGITS
     Ανακτήθηκε
    0.77
     him
    0.75
     them
    0.73
     tremendously
    0.72
    ]--;
    0.70
     us
    0.69
    AddTagHelper
    0.68
    θεν
    0.67
    ]='\
    0.66
    AddHtmlAttribute
    0.65
    Activations Density 0.544%

    No Known Activations