Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5818
    Prev
    Next
    INDEX
    Explanations

    references to popular technology and digital solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kiệm
    -0.42
    ocd
    -0.42
     šķ
    -0.40
    oa̍t
    -0.39
    小编
    -0.38
    ungkinan
    -0.38
     Colombie
    -0.38
    GetEnumerator
    -0.38
     wahrscheinlich
    -0.38
     kebanyakan
    -0.37
    POSITIVE LOGITS
    NameInMap
    0.54
     disambiguazione
    0.49
    كويكب
    0.48
     للاسماء
    0.47
    webElementXpaths
    0.47
    anmoins
    0.44
     Chhat
    0.42
    لينكات
    0.42
     Sena
    0.41
    Geplaatst
    0.40
    Activations Density 0.784%

    No Known Activations