© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 5988
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements within programming languages

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

    Code snippets with curly brackets

    np_acts-logits-general · gemini-2.0-flash

    code block delimiters

    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
     turn
    -0.47
    initComponents
    -0.47
     le
    -0.44
    róleo
    -0.44
     ro
    -0.43
     me
    -0.43
    ,
    -0.42
     free
    -0.42
    …
    -0.42
    SharedDtor
    -0.42
    POSITIVE LOGITS
     Diſ
    0.89
     AttributeSet
    0.83
     ſeveral
    0.83
     faſt
    0.78
    存于互联网档案馆
    0.77
     uſed
    0.77
     Reſ
    0.76
    Portail
    0.74
     Monfieur
    0.74
     uſe
    0.74
    Activations Density 0.093%

    No Known Activations