Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 12421
    Prev
    Next
    INDEX
    Explanations

    negations and inquiries related to health and lifestyle rationale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whether
    -0.79
     what
    -0.72
     WHETHER
    -0.71
     What
    -0.71
     how
    -0.69
     Whether
    -0.69
    whether
    -0.69
     How
    -0.68
     WHAT
    -0.67
    what
    -0.66
    POSITIVE LOGITS
     do
    1.59
     did
    1.33
     does
    1.24
    do
    0.90
     doe
    0.87
     DO
    0.83
    did
    0.81
    Do
    0.79
     Do
    0.79
     doth
    0.72
    Activations Density 0.203%

    No Known Activations