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. 14540
    Prev
    Next
    INDEX
    Explanations

    references to authors and papers in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Capital letter followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    N. Felder

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    UIControlState
    -0.85
    ftagPool
    -0.59
     gynhyrchwyd
    -0.59
    umerable
    -0.59
    modelBuilder
    -0.55
     inuti
    -0.55
    databind
    -0.54
     mourir
    -0.54
    SafeMath
    -0.53
    tvguidetime
    -0.53
    POSITIVE LOGITS
     Nellie
    0.72
     Nelly
    0.71
     veau
    0.68
     stockings
    0.68
     Nook
    0.61
    Nek
    0.61
     naa
    0.59
     Nugent
    0.59
     currentNode
    0.58
     Ns
    0.58
    Activations Density 1.328%

    No Known Activations