© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6839
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational roles, initiatives, and collaborative efforts

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

    Organizations or initiatives

    np_acts-logits-general · gemini-2.0-flash

    purpose of organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.96
    RectangleBorder
    -0.92
    HostException
    -0.77
     NSCoder
    -0.76
    +#+#
    -0.75
     виправивши
    -0.73
    BagConstraints
    -0.72
    BeginContext
    -0.71
     تضيفلها
    -0.71
    webElementXpaths
    -0.71
    POSITIVE LOGITS
     aimed
    1.17
     aims
    1.17
     aim
    0.96
     aiming
    0.96
    Aim
    0.82
     focused
    0.82
     focuses
    0.82
     launched
    0.81
    旨在
    0.81
     bertujuan
    0.80
    Activations Density 0.307%

    No Known Activations