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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 16109
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience and storytelling

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

    Expressing personal experiences

    np_acts-logits-general · gemini-2.0-flash

    lived, worked, experienced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.62
    Rüyada
    -0.60
     Normdatei
    -0.59
    iecie
    -0.58
    ecco
    -0.56
    Tracce
    -0.55
    ukone
    -0.54
    SBATCH
    -0.54
     viewDidLoad
    -0.53
     NUKAT
    -0.53
    POSITIVE LOGITS
     firsthand
    0.73
     myself
    0.72
     lived
    0.67
     experienced
    0.66
    ngdoc
    0.62
     experience
    0.62
     personally
    0.61
     personalmente
    0.58
    experienced
    0.55
    expérience
    0.54
    Activations Density 0.296%

    No Known Activations