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. 16-GEMMASCOPE-RES-16K
    6. 2893
    Prev
    Next
    INDEX
    Explanations

    nested parentheses and brackets in mathematical or programming expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝖚
    -0.76
    𝖗
    -0.64
    parms
    -0.60
     or
    -0.59
    𝖞
    -0.58
    Халык
    -0.58
    ulco
    -0.57
    plaatsen
    -0.56
     besar
    -0.56
    strSql
    -0.55
    POSITIVE LOGITS
    (((
    1.35
     intptr
    1.19
    expandindo
    1.12
    =((
    1.05
     raiſ
    1.04
    ((((
    1.01
    ((
    0.99
     ejus
    0.95
     (((
    0.94
     للمعارف
    0.94
    Activations Density 0.189%

    No Known Activations