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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105149
    Prev
    Next
    INDEX
    Explanations

    terms related to authorities and officials involved in public safety and health matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     surla
    -0.68
    StructEnd
    -0.61
    :✨
    -0.57
    ConstraintMaker
    -0.52
    uxxxx
    -0.50
    ngdoc
    -0.46
     Normdatei
    -0.46
     resourceCulture
    -0.45
    دانشنامهٔ
    -0.44
     suoi
    -0.44
    POSITIVE LOGITS
     officials
    0.61
    Officials
    0.59
     lawmakers
    0.58
    Investigators
    0.57
     investigators
    0.54
     Officials
    0.54
     negotiators
    0.53
     Investigators
    0.52
    uties
    0.51
    cillors
    0.51
    Activations Density 0.030%

    No Known Activations