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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3465
    Prev
    Next
    INDEX
    Explanations

    phrases expressing frustration or inconvenience related to waiting and logistical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.68
    Hentet
    -0.67
    tvguidetime
    -0.55
    Vanjske
    -0.52
    ittoria
    -0.52
    tanleria
    -0.51
    ртка
    -0.51
    tirol
    -0.51
    awtextra
    -0.50
     BoxFit
    -0.48
    POSITIVE LOGITS
     deal
    0.90
     dealing
    0.88
     wasting
    0.87
     waste
    0.86
     worrying
    0.82
    deal
    0.81
     worry
    0.80
     DEAL
    0.80
     wasted
    0.79
     risking
    0.79
    Activations Density 0.281%

    No Known Activations