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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20-GEMMASCOPE-RES-16K
    6. 5208
    Prev
    Next
    INDEX
    Explanations

    references to global or local variables and their usage in code

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

    Declaration of variables

    np_acts-logits-general · gemini-2.0-flash

    global and local variables

    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
    mogat
    -0.59
     /\.
    -0.56
    ellón
    -0.55
     '**
    -0.52
    ]=='
    -0.51
     ethic
    -0.50
    Bains
    -0.48
    PositiveButton
    -0.48
    Toni
    -0.48
    grano
    -0.47
    POSITIVE LOGITS
     variable
    1.80
     variables
    1.68
    variable
    1.50
     Variable
    1.45
    变量
    1.44
    Variable
    1.42
     Variables
    1.41
    variables
    1.32
     variabel
    1.28
    Variables
    1.26
    Activations Density 0.795%

    No Known Activations