© 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. 22-GEMMASCOPE-RES-16K
    11. 8145
    Prev
    Next
    INDEX
    Explanations

    code snippets related to Twitter API functionalities

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

    Twitter or tweets

    np_acts-logits-general · gemini-2.0-flash

    Twitter and tweets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.77
     Portail
    -0.72
     ujednoznacz
    -0.70
     HasFactory
    -0.67
    AnchorStyles
    -0.66
    ValueStyle
    -0.59
     Baillargeon
    -0.59
    хьтан
    -0.57
    Portail
    -0.56
     ModelRenderer
    -0.55
    POSITIVE LOGITS
     tweet
    1.76
     tweets
    1.69
     Twitter
    1.68
     tweeting
    1.64
     Tweet
    1.59
     Tweets
    1.57
     tweeted
    1.56
     twitter
    1.51
    Twitter
    1.46
    tweet
    1.42
    Activations Density 0.134%

    No Known Activations