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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15189
    Prev
    Next
    INDEX
    Explanations

    discussions and references related to philosophy

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

    "philosophy" or its inflections

    np_acts-logits-general · gemini-2.0-flash

    philosophical issues and concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of philosophy and philosophical inquiry, including discourse about studying, teaching, or discussing it.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.70
    AddTagHelper
    -0.69
    ReusableCell
    -0.67
     Administrativna
    -0.66
    +#+#
    -0.66
    fjspx
    -0.65
    upol
    -0.64
    BeginContext
    -0.63
    الإنجليزية
    -0.63
     للاسماء
    -0.62
    POSITIVE LOGITS
     philosophical
    0.65
     philosophy
    0.52
    philosop
    0.52
     philosophi
    0.51
     philosopher
    0.47
     filosof
    0.47
     filosó
    0.47
     philosophers
    0.46
    filosof
    0.45
     philosoph
    0.44
    Activations Density 0.419%

    No Known Activations