© 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. 20-GEMMASCOPE-RES-16K
    11. 820
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or scientific relationships and concepts

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

    Follows articles (a, in, the) or prepositions

    np_acts-logits-general · gemini-2.0-flash

    conversely or on the other hand

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Infórmanos
    -0.68
     particulière
    -0.65
    
    -0.64
     يتيمه
    -0.64
    AsUp
    -0.64
    Jîn
    -0.63
     erwähnten
    -0.59
    </blockquote>
    -0.58
    >*/
    -0.58
    </h3>
    -0.58
    POSITIVE LOGITS
     sebaliknya
    0.81
     наоборот
    0.78
     altrett
    0.69
     conversely
    0.68
     Conversely
    0.66
     dagegen
    0.65
    逆に
    0.64
     Sedangkan
    0.63
    另一
    0.63
    Conversely
    0.63
    Activations Density 1.825%

    No Known Activations