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. 756
    Prev
    Next
    INDEX
    Explanations

    instances of the word "managed" and its variations, especially in contexts relating to overcoming challenges or achieving something

    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
     Verantwortung
    -0.35
     Öffentlichkeit
    -0.32
     szí
    -0.30
     BrowserModule
    -0.30
     watch
    -0.29
     customers
    -0.28
     review
    -0.27
     słu
    -0.27
     others
    -0.27
     cuartos
    -0.27
    POSITIVE LOGITS
    IntoConstraints
    0.95
     CreateTagHelper
    0.85
     riuscito
    0.83
    bootstrapcdn
    0.82
    MessageTagHelper
    0.82
     jadx
    0.81
     otomatig
    0.80
    TargetException
    0.79
    ValueStyle
    0.79
    WriteTagHelper
    0.79
    Activations Density 0.281%

    No Known Activations