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. 20-GEMMASCOPE-RES-16K
    6. 13726
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions and thoughtful considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.70
    PhysRev
    -0.69
    তথ্যসূত্র
    -0.67
     CreateTagHelper
    -0.67
     كومونز
    -0.66
     kaarangay
    -0.64
    новништво
    -0.61
    UnsafeEnabled
    -0.61
    Meds
    -0.59
    umis
    -0.58
    POSITIVE LOGITS
     anyway
    3.76
     anyways
    3.13
    anyway
    3.02
     anyhow
    2.73
     Anyway
    2.71
    Anyway
    2.67
     Anyways
    2.09
    Anyways
    2.01
     ohnehin
    1.85
    Anyhow
    1.85
    Activations Density 0.386%

    No Known Activations