© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16363
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical characteristics or attributes

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

    information being shared or presented in professional contexts like resumes, CVs, or personal documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    期刊论文
    -0.43
    RegistryLite
    -0.42
    RegressionTest
    -0.38
    expandindo
    -0.37
     semestre
    -0.37
    oquia
    -0.36
    AUTHORS
    -0.34
    ſt
    -0.34
    AddTagHelper
    -0.34
    oneofs
    -0.33
    POSITIVE LOGITS
     ComVisible
    0.52
     attracting
    0.48
    presentation
    0.48
    PMailer
    0.46
     ویکی‌پدی
    0.46
     Préférences
    0.46
     attracts
    0.46
    queryInterface
    0.45
     presentation
    0.45
     attract
    0.44
    Activations Density 0.270%

    No Known Activations