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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 441
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures, particularly pairs and tuples

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

    Parentheses, pairs, or tuples

    np_acts-logits-general · gemini-2.0-flash

    pairs and tuples

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    IntoConstraints
    -0.63
    MessageTagHelper
    -0.60
     оригіналу
    -0.57
    rrggbb
    -0.57
    पया
    -0.51
    loroethene
    -0.50
    tonode
    -0.50
    脚注の使い方
    -0.50
    __(/*!
    -0.49
     protoimpl
    -0.49
    POSITIVE LOGITS
     pair
    0.61
     pairs
    0.60
     paire
    0.58
     couples
    0.57
     couple
    0.56
     coppia
    0.54
     pairing
    0.54
     duo
    0.53
     parejas
    0.51
     pareja
    0.50
    Activations Density 0.908%

    No Known Activations