© 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. 521
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and phrases related to methodology and outcomes in research studies

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

    technical or scientific terminology and phrases, particularly related to medical research and gene mutations.

    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
    OGND
    -0.90
     Chwiliwch
    -0.90
    Personendaten
    -0.79
    الحياه
    -0.70
     незавершена
    -0.68
     surla
    -0.68
    sidemargin
    -0.68
     snippetHide
    -0.66
    featureID
    -0.66
     HasFactory
    -0.66
    POSITIVE LOGITS
     Them
    0.41
     Including
    0.34
     Kid
    0.33
     Old
    0.33
     Top
    0.33
    圖片來源
    0.32
     Worth
    0.32
     Man
    0.32
    greif
    0.32
     Bar
    0.31
    Activations Density 0.451%

    No Known Activations