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. 3608
    Prev
    Next
    INDEX
    Explanations

    terms related to accreditation and certification in professional contexts

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

    Accreditation, certifications, or approval

    np_acts-logits-general · gemini-2.0-flash

    certification and accreditation

    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
     '\\;'
    -0.65
     FetchType
    -0.64
    ArgsConstructor
    -0.64
     الرياضيه
    -0.63
    MigrationBuilder
    -0.56
    AndEndTag
    -0.53
    AccessFile
    -0.53
    endphp
    -0.52
    
    -0.51
    ']))
    
    -0.51
    POSITIVE LOGITS
     certification
    0.77
     certified
    0.69
     Certification
    0.65
    certification
    0.64
     certifications
    0.63
     Certified
    0.61
    Certification
    0.61
    certified
    0.60
     certify
    0.60
     certificación
    0.57
    Activations Density 0.146%

    No Known Activations