© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105693
    Prev
    Next
    INDEX
    Explanations

    instances of curly braces or code block delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     wikipagina
    -0.54
    뀐
    -0.45
     culture
    -0.45
     cultural
    -0.43
     cult
    -0.42
    updateUser
    -0.42
    リンゴ
    -0.41
     photographs
    -0.41
    その他の
    -0.41
     pet
    -0.40
    POSITIVE LOGITS
    SharedDtor
    0.65
     ब्रेकडाउन
    0.58
    __":
    0.57
    __':
    0.57
    __':
    0.57
     beginnetje
    0.53
    GOTREF
    0.52
    __":
    0.50
    SharedCtor
    0.48
    CDCl
    0.46
    Activations Density 0.006%

    No Known Activations