© 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. 4599
    Prev
    Next
    INDEX
    Explanations

    items related to programming errors or issues in code execution

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

    references to academic or medical documentation and technical discussions.

    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
    webElementXpaths
    -0.81
    Personendaten
    -0.73
    enderror
    -0.65
    UserScript
    -0.65
     rhestr
    -0.65
    IUrlHelper
    -0.62
     kasarigan
    -0.61
    发表于
    -0.59
    XMLSchema
    -0.59
    $_['
    -0.58
    POSITIVE LOGITS
    sizeCache
    0.44
     fos
    0.38
     nahilalakip
    0.38
     initComponents
    0.33
     Hatton
    0.32
     vol
    0.32
    prevState
    0.32
     conval
    0.31
    hallen
    0.30
     öppna
    0.30
    Activations Density 0.114%

    No Known Activations