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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53787
    Prev
    Next
    INDEX
    Explanations

    structured data elements or syntax used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ThemeData
    -0.54
     defaultstate
    -0.52
     '\\;'
    -0.46
     خص
    -0.45
    原始内容存档
    -0.45
    BufferException
    -0.45
     pseudonym
    -0.45
     Counter
    -0.43
     MutableLiveData
    -0.43
     SUBST
    -0.42
    POSITIVE LOGITS
     nakalista
    0.49
    Manbalar
    0.46
    CPtr
    0.45
     ब्रेकडाउन
    0.43
    queles
    0.41
     étrangères
    0.41
    matchCondition
    0.41
    новниш
    0.40
     either
    0.40
    Rüyada
    0.39
    Activations Density 0.008%

    No Known Activations