Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8622
    Prev
    Next
    INDEX
    Explanations

    elements related to coding syntax and structure in programming languages

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    code snippets and punctuation

    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
     itſelf
    -1.30
     iſt
    -1.29
     ―――――
    -1.23
     myſelf
    -1.18
     ſind
    -1.18
    ſelves
    -1.16
    >\<^
    -1.16
    ^(@)
    -1.15
     ་་
    -1.14
    !")
    
    -1.13
    POSITIVE LOGITS
    ↵↵
    1.24
    ↵
    1.20
     ,
    1.09
    <eos>
    1.02
     This
    0.99
     -
    0.99
     .
    0.94
     (
    0.93
     or
    0.92
    .
    0.90
    Activations Density 0.959%

    No Known Activations