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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 462
    Prev
    Next
    INDEX
    Explanations

    key roles and responsibilities related to service-oriented professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.48
    ctools
    -0.47
    참고
    -0.46
     plumes
    -0.44
     Researcher
    -0.44
     panelists
    -0.44
     XNUMX
    -0.43
    Пока
    -0.43
    Researcher
    -0.43
     Reviewer
    -0.43
    POSITIVE LOGITS
     whether
    0.88
    Whether
    0.84
     Whether
    0.84
    whether
    0.76
     contact
    0.69
     WHETHER
    0.69
    contact
    0.63
    Contact
    0.63
     Contact
    0.62
     CONTACT
    0.61
    Activations Density 0.145%

    No Known Activations