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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15913
    Prev
    Next
    INDEX
    Explanations

    recently announced or established actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventually
    -0.59
     uiteindelijk
    -0.58
     ultimately
    -0.58
     inicialmente
    -0.58
     pengar
    -0.57
     ursprünglich
    -0.56
     Ultimately
    -0.54
     Eventually
    -0.52
     eredeti
    -0.52
    Eventually
    -0.51
    POSITIVE LOGITS
    recently
    0.79
     recently
    0.78
    elemField
    0.73
     newest
    0.69
     frisch
    0.68
     newly
    0.67
     recente
    0.66
     недавно
    0.66
     nakalista
    0.66
     recientemente
    0.65
    Activations Density 0.184%

    No Known Activations