© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2786
    Prev
    Next
    INDEX
    Explanations

    key statistical terms and variables related to data analysis in a structured format

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

    programming code elements related to batting statistics in cricket or baseball.

    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
     مرئيه
    -0.74
    MessageTagHelper
    -0.60
    MessageOf
    -0.59
    Geplaatst
    -0.54
    ContentAsync
    -0.54
    featureID
    -0.52
     للاسماء
    -0.50
    LookAnd
    -0.50
     برانيه
    -0.50
    stateProvider
    -0.50
    POSITIVE LOGITS
     examined
    0.44
    exam
    0.43
     tillgäng
    0.43
    Exam
    0.42
     Exam
    0.41
     examinations
    0.40
     exam
    0.40
     volume
    0.40
     sample
    0.40
     evaluated
    0.39
    Activations Density 0.471%

    No Known Activations