© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4005
    Prev
    Next
    INDEX
    Explanations

    references to academic awards and educational institutions

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

    information about academic and professional credentials, particularly scholarly achievements and institutional affiliations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     pinulongan
    -0.62
     يتيمه
    -0.59
     kasarigan
    -0.59
    хьтан
    -0.58
    -------------</
    -0.57
    OGND
    -0.54
    
    -0.54
     дописавши
    -0.53
     informée
    -0.53
    PhysRev
    -0.52
    POSITIVE LOGITS
     scholarships
    0.45
     scholarship
    0.41
     donation
    0.39
     Stiftung
    0.38
     endowment
    0.38
     perpetuity
    0.37
     MERCHANTABILITY
    0.37
     Memorial
    0.37
     memorial
    0.36
     donor
    0.36
    Activations Density 0.078%

    No Known Activations