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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1129
    Prev
    Next
    INDEX
    Explanations

    elements related to the legal process and procedures, particularly those involving testimony and questioning

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

    references to semi-structured interviews and their design

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

    asking questions or interviewing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ServiceProvider
    -0.53
     فريبيس
    -0.53
     péld
    -0.52
     vœ
    -0.52
    lages
    -0.52
     revend
    -0.50
     fourrure
    -0.49
    relser
    -0.49
     doInBackground
    -0.49
     campañas
    -0.49
    POSITIVE LOGITS
     interview
    1.75
     interviewing
    1.70
     interviewer
    1.67
    interview
    1.59
     questioning
    1.55
     Interview
    1.54
     interrogation
    1.53
     questions
    1.52
     interrog
    1.51
    Interview
    1.49
    Activations Density 0.337%

    No Known Activations