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. 20-GEMMASCOPE-RES-16K
    6. 5075
    Prev
    Next
    INDEX
    Explanations

    instances of the word "throughout."

    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
    ⓧ
    -0.62
    Tikang
    -0.59
    ransition
    -0.50
    Personendaten
    -0.49
    yargs
    -0.49
     drill
    -0.49
    jSON
    -0.48
     injector
    -0.48
     Drill
    -0.48
    nastics
    -0.48
    POSITIVE LOGITS
     throughout
    1.43
    throughout
    1.38
     Throughout
    1.16
    Throughout
    1.15
     sepanjang
    0.77
     entire
    0.76
     suốt
    0.75
     boyunca
    0.73
     everywhere
    0.71
     בכל
    0.71
    Activations Density 0.058%

    No Known Activations