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. 2-GEMMASCOPE-RES-16K
    6. 6698
    Prev
    Next
    INDEX
    Explanations

    references to the number "five" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secund
    -0.58
     addSubview
    -0.58
     two
    -0.58
    "}";
    -0.58
     sectional
    -0.57
     Reap
    -0.56
     Baillargeon
    -0.55
    peat
    -0.55
    туа
    -0.54
    stackoverflow
    -0.54
    POSITIVE LOGITS
     Five
    2.04
    Five
    1.89
    five
    1.85
    FIVE
    1.83
     FIVE
    1.80
     five
    1.64
     Fifth
    1.47
    fifth
    1.45
     Fünf
    1.43
     fünf
    1.42
    Activations Density 0.058%

    No Known Activations