Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13710
    Prev
    Next
    INDEX
    Explanations

    references to companies and their classifications or legal designations

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

    Company name abbreviations

    np_acts-logits-general · gemini-2.0-flash

    company suffixes like Ltd and Inc

    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
    httphttps
    -0.87
    verifyException
    -0.77
     nahilalakip
    -0.75
    Jîn
    -0.64
    ]")]
    -0.64
    oplayer
    -0.62
    fjspx
    -0.60
     podjela
    -0.59
    wpi
    -0.59
    GEBURTSDATUM
    -0.57
    POSITIVE LOGITS
     Ltd
    0.87
     Inc
    0.86
     LLC
    0.73
     Corporation
    0.70
     Company
    0.68
     ltd
    0.66
    Ltd
    0.64
     Limited
    0.63
     corporation
    0.59
     LTD
    0.59
    Activations Density 0.116%

    No Known Activations