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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53191
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character 'n' in various contexts

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

    pattern, suffix, GET, confronted

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ✨:
    -0.69
     împreună
    -0.60
     InputDecoration
    -0.58
     Lyle
    -0.58
    Transcription
    -0.57
     Roskov
    -0.57
    ässig
    -0.56
    プリング
    -0.55
     Gallimard
    -0.52
    dag
    -0.50
    POSITIVE LOGITS
    Спасылкі
    0.69
     ffilmiau
    0.67
    dafx
    0.64
    исленность
    0.62
     turb
    0.61
    mstyle
    0.60
     AssemblyVersion
    0.59
    sern
    0.57
     Ucraina
    0.57
    ьаж
    0.57
    Activations Density 0.004%

    No Known Activations