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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4247
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "App" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Tar
    -0.47
     besar
    -0.45
    Zel
    -0.45
    duğu
    -0.44
     kháng
    -0.44
    SourceChecksum
    -0.43
     sich
    -0.42
     Tar
    -0.42
     prise
    -0.42
    сты
    -0.42
    POSITIVE LOGITS
     getApp
    0.91
    getApp
    0.87
     ftate
    0.83
     doubtnut
    0.81
     itſelf
    0.80
     ſtate
    0.79
     Majefty
    0.79
     apps
    0.78
     APP
    0.77
    Portály
    0.76
    Activations Density 0.114%

    No Known Activations