© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104557
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to agreements and contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     conducting
    -0.33
    klär
    -0.33
     Kredit
    -0.33
    приятие
    -0.32
     vs
    -0.32
     onBackPressed
    -0.32
    atche
    -0.32
    ")));
    
    -0.31
     "))
    -0.31
     Al
    -0.31
    POSITIVE LOGITS
     AssemblyCulture
    0.69
     propOrder
    0.66
     ویکی‌پدی
    0.66
    httphttps
    0.60
     snippetHide
    0.60
    ########.
    0.59
    kháu
    0.59
    OGND
    0.59
     rhestr
    0.56
     pinulongan
    0.56
    Activations Density 0.075%

    No Known Activations