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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 87661
    Prev
    Next
    INDEX
    Explanations

    terms related to academic contributions and processes in research writing

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

    Author Contributions, supplementary material

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    savage
    -0.39
    effetto
    -0.38
    xampp
    -0.37
    Inverted
    -0.37
     Italijanski
    -0.36
     vực
    -0.34
    ército
    -0.34
    hopefully
    -0.34
     industriels
    -0.34
    sciences
    -0.34
    POSITIVE LOGITS
    Correspondence
    1.03
     Correspondence
    0.93
     correspondence
    0.76
    PerformLayout
    0.73
     correspond
    0.64
    correspond
    0.63
     corresponde
    0.58
     correspondance
    0.57
    StoryboardSegue
    0.55
     GenerationType
    0.54
    Activations Density 0.002%

    No Known Activations