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. 5-GEMMASCOPE-RES-16K
    6. 8587
    Prev
    Next
    INDEX
    Explanations

    requests related to sending and receiving messages or photos via email or other communication methods

    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
    DockStyle
    -0.77
    verwijspagina
    -0.66
     Normdatei
    -0.65
     resultSet
    -0.63
    InjectAttribute
    -0.60
    awtextra
    -0.59
    HostException
    -0.59
    ArgsConstructor
    -0.59
    TintMode
    -0.59
    mybatisplus
    -0.58
    POSITIVE LOGITS
     sent
    1.61
     send
    1.51
     sending
    1.51
     Sends
    1.44
     sends
    1.42
     Sending
    1.42
     Send
    1.35
    Send
    1.35
     Sent
    1.32
    Sending
    1.31
    Activations Density 0.184%

    No Known Activations