© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14613
    Prev
    Next
    INDEX
    Explanations

    issues related to health and medical conditions

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

    Followed by "never" (or similar negative)

    np_acts-logits-general · gemini-2.0-flash

    common verbs followed by never

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.65
     rospy
    -0.64
     CURIAM
    -0.58
    IsMutable
    -0.57
    StoreMessageInfo
    -0.56
    脚注の使い方
    -0.56
    :]:
    -0.55
    tonsoft
    -0.55
     متعلقه
    -0.54
    MLLoader
    -0.54
    POSITIVE LOGITS
     never
    3.53
    never
    2.94
     Never
    2.90
    Never
    2.79
     NEVER
    2.50
     nunca
    2.41
     nigdy
    2.33
    NEVER
    2.32
     никогда
    2.13
     nooit
    2.10
    Activations Density 0.327%

    No Known Activations