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. 9-GEMMASCOPE-RES-16K
    6. 3879
    Prev
    Next
    INDEX
    Explanations

    words with special diacritics or accents

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

    Tokens with diacritics

    np_acts-logits-general · gemini-2.0-flash

    accented vowels followed by `]{`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.57
     stanga
    -0.56
     المعيارى
    -0.55
    Garcia
    -0.52
     viata
    -0.52
    linawan
    -0.52
     przec
    -0.50
     nahilalakip
    -0.49
    atoare
    -0.49
    !*\
    -0.48
    POSITIVE LOGITS
    <?
    0.63
     vPvB
    0.54
     MÉXICO
    0.51
     jSON
    0.50
     Erdoğan
    0.48
    {§
    0.47
     láser
    0.47
     Renée
    0.46
    ByID
    0.44
     leſs
    0.44
    Activations Density 0.655%

    No Known Activations