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. 17-GEMMASCOPE-RES-16K
    6. 7217
    Prev
    Next
    INDEX
    Explanations

    confirmation prompts related to actions like deleting or removing accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TryGetValue
    -0.48
    Билгалдахарш
    -0.46
    собенности
    -0.45
    crawl
    -0.44
    庁
    -0.43
    きたいと思います
    -0.43
    くださいね
    -0.41
    entikan
    -0.40
    Източници
    -0.40
    ContentAsync
    -0.40
    POSITIVE LOGITS
    confirm
    1.20
     confirmation
    1.16
    Confirm
    1.13
     Confirmation
    1.11
     Confirm
    1.11
    Confirmation
    1.08
     confirm
    1.04
    CONFIRM
    1.00
    confirmation
    0.98
     confirmations
    0.96
    Activations Density 0.145%

    No Known Activations