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. 16107
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the realities and challenges of life, particularly in relation to injuries and the nature of circumstances

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

    "Part of" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    part of

    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
    omie
    -0.48
    पू
    -0.46
     closed
    -0.46
    idia
    -0.44
    置き
    -0.44
    hawatir
    -0.44
    infty
    -0.44
     aufgehoben
    -0.44
     reference
    -0.43
    imov
    -0.42
    POSITIVE LOGITS
     unavoidable
    0.92
    AddTagHelper
    0.79
     inescapable
    0.77
     дописавши
    0.76
     inevit
    0.74
    ">//
    0.73
    PerformLayout
    0.72
     مشين
    0.72
     realities
    0.71
     unavoid
    0.71
    Activations Density 0.271%

    No Known Activations