© 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. 3822
    Prev
    Next
    INDEX
    Explanations

    code and technical terminology related to database operations and distributed computing

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

    technical code syntax and data processing operations, especially related to database and big data processing frameworks like Spark and Redis.

    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
     öz
    -0.40
     personnelle
    -0.39
    IContainer
    -0.36
     zufolge
    -0.35
    ニュアル
    -0.35
    BindingResult
    -0.33
    føl
    -0.33
     orçamento
    -0.31
     orally
    -0.31
    __;
    -0.31
    POSITIVE LOGITS
    ंदीखरीदारी
    0.60
     noDo
    0.60
    hbase
    0.59
    hadoop
    0.54
     Exacts
    0.54
     مشين
    0.53
    writeFieldEnd
    0.53
    estries
    0.53
     infrastructure
    0.52
     operational
    0.52
    Activations Density 0.345%

    No Known Activations