© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 14831
    Prev
    Next
    INDEX
    Explanations

    words or phrases expressing strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pagni
    -0.59
     مرئيه
    -0.56
     Bhd
    -0.55
    IVITY
    -0.55
    Autoritní
    -0.55
     Ber
    -0.53
     secteurs
    -0.52
     scio
    -0.52
    regulated
    -0.51
     expansion
    -0.51
    POSITIVE LOGITS
    AsUp
    0.74
     betweenstory
    0.68
    ungsbedingungen
    0.67
     متعلقه
    0.65
     оригіналу
    0.63
    énario
    0.62
    IntoConstraints
    0.59
    tagHelperRunner
    0.56
     Dafür
    0.56
     yours
    0.55
    Activations Density 0.464%

    No Known Activations