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. 5-GEMMASCOPE-RES-16K
    6. 4806
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ask" 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GameData
    -0.75
    rowData
    -0.71
     tider
    -0.70
    достатки
    -0.69
     Dorado
    -0.67
    paraiso
    -0.67
    adze
    -0.66
    Здра
    -0.65
     Bhd
    -0.65
     Dresden
    -0.63
    POSITIVE LOGITS
     ask
    2.38
     asks
    2.24
     Ask
    2.16
     asking
    2.12
    Ask
    2.11
     ASK
    2.10
     asked
    2.10
     Asking
    2.05
    Asking
    2.01
    ask
    1.83
    Activations Density 0.039%

    No Known Activations