© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 593
    Prev
    Next
    INDEX
    Explanations

    code constructs related to task management in a build system

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

    occurrences of code related to file processing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     AttributeSet
    -0.59
     emprunt
    -0.57
    WithIOException
    -0.54
     tilla
    -0.54
     CURLOPT
    -0.47
    شهاد
    -0.46
    InitStructure
    -0.46
     FUNERAL
    -0.46
    vestido
    -0.46
    rungs
    -0.46
    POSITIVE LOGITS
    CrossRef
    0.63
    DockStyle
    0.55
    ributor
    0.51
     שוליים
    0.50
    wisata
    0.50
     Bentley
    0.50
    hasData
    0.50
     Oppen
    0.48
    期刊论文
    0.48
    ]--;
    0.48
    Activations Density 0.070%

    No Known Activations