© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4184
    Prev
    Next
    INDEX
    Explanations

    code snippets involving user data, specifically related to Twitter account information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URLs or text related to Twitter

    np_acts-logits-general · gemini-2.0-flash

    twitter posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spoljašnje
    -0.84
     HasFactory
    -0.69
     Portail
    -0.66
     ModelRenderer
    -0.66
     ujednoznacz
    -0.60
    хьтан
    -0.60
     GreatSchools
    -0.58
    ValueStyle
    -0.58
    resave
    -0.57
    SceneManagement
    -0.57
    POSITIVE LOGITS
     tweet
    2.06
     tweets
    2.01
     Twitter
    1.92
     tweeting
    1.92
     Tweet
    1.87
     Tweets
    1.83
     tweeted
    1.82
     twitter
    1.75
    Tweet
    1.68
    tweet
    1.68
    Activations Density 0.164%

    No Known Activations