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. 16-GEMMASCOPE-RES-16K
    6. 6137
    Prev
    Next
    INDEX
    Explanations

    emotional and impactful descriptors related to distress and turmoil

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

    ending in "ing" or "ly."

    np_acts-logits-general · gemini-2.0-flash

    negative and shocking descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GlobalKey
    -0.69
    ंदीखरीदारी
    -0.61
     Wiktionnaire
    -0.57
     resourceCulture
    -0.57
     MonoBehaviour
    -0.56
     AssemblyCulture
    -0.56
    mybatisplus
    -0.56
    httphttps
    -0.55
    JOptionPane
    -0.55
    glGen
    -0.55
    POSITIVE LOGITS
    ly
    1.02
    ingly
    0.72
    tingly
    0.67
    ivably
    0.67
    weise
    0.65
    eably
    0.64
    ably
    0.63
    RenderAtEndOf
    0.58
    itous
    0.57
    mente
    0.56
    Activations Density 0.299%

    No Known Activations