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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 15794
    Prev
    Next
    INDEX
    Explanations

    instances of the word "examine" and related terms indicating investigation or analysis

    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-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
     queſta
    -0.70
     esternos
    -0.67
     Administrativna
    -0.64
     يتيمه
    -0.63
    migrationBuilder
    -0.60
     kaarangay
    -0.59
    jsonwebtoken
    -0.58
     myſelf
    -0.57
    uxxxx
    -0.57
     kasarigan
    -0.57
    POSITIVE LOGITS
     examining
    0.81
     Examine
    0.73
     examines
    0.72
     Examining
    0.71
     examine
    0.71
     analysing
    0.67
     examined
    0.67
     analizar
    0.66
     analyzing
    0.65
     consideration
    0.65
    Activations Density 0.433%

    No Known Activations