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. 924
    Prev
    Next
    INDEX
    Explanations

    statements or claims regarding political events or testimonies

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

    Tokens after a date, often a year

    np_acts-logits-general · gemini-2.0-flash

    same day, year, or time

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    كويكب
    -0.44
    addAttribute
    -0.44
    enterOuterAlt
    -0.42
     laiko
    -0.41
    gemeester
    -0.40
     opinion
    -0.39
    SourceChecksum
    -0.38
    quina
    -0.38
    bag
    -0.37
    Bag
    -0.37
    POSITIVE LOGITS
     simultaneously
    0.73
    simult
    0.72
    Simult
    0.69
     simultaneous
    0.68
     Simultaneously
    0.67
     concurrent
    0.64
     concurrently
    0.63
     simult
    0.61
     Concurrent
    0.59
     Simultaneous
    0.55
    Activations Density 0.529%

    No Known Activations