© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 40559
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to claims and liabilities

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

    or, other, and/or

    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
    /**
    -0.47
     îna
    -0.41
    zeptember
    -0.40
     utafitiHapana
    -0.39
     屋根
    -0.36
    SharedCtor
    -0.35
     tramonto
    -0.34
    Autoritní
    -0.34
     المعيارى
    -0.34
    liyor
    -0.34
    POSITIVE LOGITS
     whatsoever
    0.57
     CreateTagHelper
    0.56
    ActionEvent
    0.50
     صوتيه
    0.50
     any
    0.50
     cualquier
    0.50
     qualsiasi
    0.50
     ANYTHING
    0.48
    soever
    0.48
     ANY
    0.48
    Activations Density 0.067%

    No Known Activations