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. 20-GEMMASCOPE-RES-16K
    6. 4573
    Prev
    Next
    INDEX
    Explanations

    statements and debates regarding government actions and decisions, particularly related to social issues like refugee policies

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

    Tokens preceding numerical values or estimations

    np_acts-logits-general · gemini-2.0-flash

    numerical figures and estimates

    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
    ReferenceEquals
    -0.47
    iados
    -0.46
     egyszer
    -0.45
    一面
    -0.44
     hasattr
    -0.43
    ばかり
    -0.42
    Purpose
    -0.42
    liesslich
    -0.42
    nements
    -0.42
    ędziesz
    -0.41
    POSITIVE LOGITS
     cifra
    1.04
     numbers
    1.00
     chiffre
    0.98
     chiffres
    0.98
     figures
    0.94
     totals
    0.92
     estimate
    0.91
     циф
    0.91
     figure
    0.89
    數字
    0.89
    Activations Density 0.497%

    No Known Activations