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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15942
    Prev
    Next
    INDEX
    Explanations

    terms related to formal procedures and grievance reporting

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

    preceding "of" or following quotations/legal language

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dodgy
    -0.74
     maths
    -0.72
     favourite
    -0.61
     civilisation
    -0.60
    favourite
    -0.59
     colour
    -0.59
     organisers
    -0.58
     aluminium
    -0.57
     haem
    -0.56
     hugely
    -0.56
    POSITIVE LOGITS
     pursuant
    0.88
     utilizing
    0.82
     utilized
    0.74
     Pursuant
    0.73
     statewide
    0.72
     jurisdictional
    0.72
     Utilizing
    0.70
     Statewide
    0.69
    utilized
    0.68
     herein
    0.67
    Activations Density 2.321%

    No Known Activations