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. 117321
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or dissatisfaction

    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
     disambiguazione
    -0.66
     ujednoznacz
    -0.61
     itſelf
    -0.57
     poffible
    -0.56
    AndEndTag
    -0.56
     tranſ
    -0.53
    verwijspagina
    -0.53
    şiv
    -0.52
    expandindo
    -0.50
     faſt
    -0.48
    POSITIVE LOGITS
     fucking
    0.58
     fuck
    0.54
     fuckin
    0.53
     shitty
    0.53
     I
    0.53
     shit
    0.52
     fucked
    0.48
     fucker
    0.47
     racist
    0.47
     hell
    0.45
    Activations Density 0.021%

    No Known Activations