Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73696
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements related to various items, particularly in scientific and industrial contexts

    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
     defaultstate
    -0.77
     للاسماء
    -0.70
    GEBURTSDATUM
    -0.52
     Photocase
    -0.52
     utafitiHapana
    -0.51
    URLException
    -0.48
    
    -0.47
     PartialEq
    -0.45
     indisponible
    -0.45
    Autoritní
    -0.44
    POSITIVE LOGITS
     cuchara
    0.42
     CanadaChoose
    0.38
    JsonNode
    0.36
    __*/
    0.36
    jms
    0.35
    NewRow
    0.34
    StandardCharsets
    0.33
    tanleria
    0.32
     khuẩn
    0.32
     BCS
    0.32
    Activations Density 0.095%

    No Known Activations