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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1620
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and economic indicators

    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
    <?
    -0.47
     CreateTagHelper
    -0.46
     للاسماء
    -0.45
     المعيارى
    -0.44
    UrlResolution
    -0.38
    bootstrapcdn
    -0.38
    पया
    -0.38
     للمعارف
    -0.38
    hematics
    -0.37
     yet
    -0.35
    POSITIVE LOGITS
     domino
    0.68
     snowball
    0.54
    domino
    0.50
    ついでに
    0.44
     weitere
    0.42
    prop
    0.41
     slippery
    0.41
     Tenden
    0.40
     AppCompatTheme
    0.40
    verwijspagina
    0.39
    Activations Density 0.440%

    No Known Activations