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. 22-GEMMASCOPE-RES-16K
    6. 13963
    Prev
    Next
    INDEX
    Explanations

    declarations of public functions in asynchronous programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.56
     Orts
    -0.51
    stoß
    -0.45
     všetko
    -0.44
     kollu
    -0.43
    els
    -0.42
     đáo
    -0.42
    leqq
    -0.41
     ?>/
    -0.41
     pfalz
    -0.41
    POSITIVE LOGITS
     مشين
    0.71
    olingo
    0.65
     useAppContext
    0.59
    enumii
    0.59
     metav
    0.55
    GetAxis
    0.55
    nitive
    0.54
    Suara
    0.53
    期刊论文
    0.53
    orative
    0.52
    Activations Density 0.062%

    No Known Activations