© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105855
    Prev
    Next
    INDEX
    Explanations

    names and references to individuals or entities, particularly focusing on notable actions or events associated with them

    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
    躇
    -0.67
    łog
    -0.52
     BoxDecoration
    -0.43
     LoginForm
    -0.42
    onView
    -0.42
    ĝ
    -0.41
     Fisk
    -0.41
     onData
    -0.41
     befind
    -0.40
    inose
    -0.40
    POSITIVE LOGITS
     Tampere
    0.67
    Cruel
    0.67
    Reina
    0.63
     Jeremy
    0.61
     Turner
    0.59
     Cruel
    0.59
    mpu
    0.59
    Jeremy
    0.59
     Reina
    0.58
    Turner
    0.58
    Activations Density 0.011%

    No Known Activations