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. 21-GEMMASCOPE-RES-16K
    6. 1008
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize repetition or insistence, particularly the word "again"

    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
    ftagPool
    -0.57
     kteří
    -0.53
     []).
    -0.52
    [@"
    -0.52
     useAppContext
    -0.52
    €¢
    -0.50
    o
    -0.50
    nestjs
    -0.50
    vfs
    -0.49
    rainian
    -0.48
    POSITIVE LOGITS
    sidemargin
    0.72
     <=",
    0.69
    enumi
    0.67
     Paglinawan
    0.67
    igshid
    0.67
    AccessException
    0.67
    ruptedException
    0.67
    kháu
    0.66
     Audiodateien
    0.66
    ts
    0.65
    Activations Density 0.053%

    No Known Activations