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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103037
    Prev
    Next
    INDEX
    Explanations

    concepts and relationships related to conflict and opposition in social or philosophical contexts

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

    The token patterns identify relationships between paired or contrasting elements, typically using conjunctions like "and" or prepositions like "between," "of," "in," "from," etc. These connections often link contrasting concepts, parallel items in a series, or components of a larger system.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    المكان
    -0.59
    AnchorStyles
    -0.56
    IsMutable
    -0.53
    RegressionTest
    -0.52
    AndEndTag
    -0.52
    DockStyle
    -0.50
    RRect
    -0.49
    ResumeLayout
    -0.49
     ConstraintSet
    -0.48
    GOTREF
    -0.47
    POSITIVE LOGITS
     between
    0.58
     между
    0.47
     pair
    0.45
     pairs
    0.42
     tussen
    0.42
     zwischen
    0.41
     antara
    0.41
     mellan
    0.41
     duel
    0.40
     giữa
    0.39
    Activations Density 0.280%

    No Known Activations