© 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. 13597
    Prev
    Next
    INDEX
    Explanations

    sections discussing experimental results and their implications

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    code endings and list separators

    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
     Let
    -0.59
     Lets
    -0.58
     Sometimes
    -0.56
     lets
    -0.55
     Anything
    -0.55
    Sometimes
    -0.55
     every
    -0.55
    Let
    -0.54
     anything
    -0.53
     Natürlich
    -0.53
    POSITIVE LOGITS
    Consistent
    0.93
     Consistent
    0.92
     Interestingly
    0.88
     الحره
    0.87
    urlpatterns
    0.84
    Interestingly
    0.83
    tagHelperRunner
    0.82
     interestingly
    0.79
     Significantly
    0.79
     Surprisingly
    0.79
    Activations Density 1.364%

    No Known Activations