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. 24-GEMMASCOPE-RES-16K
    6. 12821
    Prev
    Next
    INDEX
    Explanations

    phrases expressing caution or recommendations

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

    Following "you," "I," or "t"

    np_acts-logits-general · gemini-2.0-flash

    notice

    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
    -0.61
    TintMode
    -0.59
    tagHelperRunner
    -0.56
    دانشنامهٔ
    -0.56
    GraphicsUnit
    -0.53
    حياتها
    -0.52
    oader
    -0.51
     wireType
    -0.51
     bulunabilir
    -0.50
    
    -0.50
    POSITIVE LOGITS
     notice
    0.83
     notices
    0.78
     noticed
    0.76
     noticing
    0.74
    notice
    0.67
    Notices
    0.66
    noticed
    0.65
     Notice
    0.63
     NOTICE
    0.62
    Notice
    0.62
    Activations Density 0.214%

    No Known Activations