© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10535
    Prev
    Next
    INDEX
    Explanations

    references to job titles and organizational roles within various contexts, particularly in the fields of corporate and public service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ները
    -0.51
    therly
    -0.51
    pieler
    -0.50
     باخ
    -0.49
    didSet
    -0.49
    blij
    -0.48
    dians
    -0.48
     Surname
    -0.47
    miştir
    -0.47
     Soldier
    -0.45
    POSITIVE LOGITS
     chief
    0.67
    ⓧ
    0.67
     ویکی‌پدیای
    0.65
     Chief
    0.65
     assistant
    0.64
    QMetaType
    0.63
    -------------</
    0.62
    ----</
    0.61
     Assistant
    0.61
    protoimpl
    0.61
    Activations Density 0.260%

    No Known Activations