© 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. 15411
    Prev
    Next
    INDEX
    Explanations

    issues related to technology utilization and personal experiences with modern advancements

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

    following conjunctions or interjections

    np_acts-logits-general · gemini-2.0-flash

    and boom

    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
    hoeddwyd
    -0.63
     للمعارف
    -0.61
    MessageOf
    -0.58
    multer
    -0.57
     فريبيس
    -0.57
     HttpNotFound
    -0.56
    NUMX
    -0.56
     hefyd
    -0.56
    ίων
    -0.54
    iastes
    -0.54
    POSITIVE LOGITS
     voila
    1.16
     bam
    1.11
     boom
    1.09
     here
    1.08
     guess
    1.05
     voilà
    1.02
     BOOM
    0.99
     behold
    0.97
     presto
    0.96
     Guess
    0.93
    Activations Density 0.185%

    No Known Activations