© 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. 24-GEMMASCOPE-RES-131K
    11. 595
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or identifiers related to data or statistics

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

    pending in, the atomic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.79
    GEBURTSDATUM
    -0.71
     AssemblyTitle
    -0.68
     Infórmanos
    -0.65
     فريبيس
    -0.65
    NameInMap
    -0.63
    出版年
    -0.63
    
    -0.62
     CreateTagHelper
    -0.61
    Datuak
    -0.60
    POSITIVE LOGITS
    teardown
    0.35
     appeared
    0.33
     cortesía
    0.31
     domaine
    0.31
     Ceará
    0.31
    LOOP
    0.31
     appear
    0.31
     âgées
    0.30
     berusia
    0.30
     Moisés
    0.30
    Activations Density 0.000%

    No Known Activations