© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12892
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to music and entertainment, particularly focusing on artists and their careers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vicina
    -0.55
     wikipagina
    -0.55
     normaux
    -0.53
     Carriers
    -0.52
     béné
    -0.51
     ktorí
    -0.51
     superiore
    -0.50
    CodeAttribute
    -0.49
     nôtre
    -0.48
     akik
    -0.48
    POSITIVE LOGITS
     former
    1.22
     ex
    0.99
    Former
    0.95
     Former
    0.92
    former
    0.90
     veteran
    0.90
     diminutive
    0.82
     youngster
    0.79
     seasoned
    0.78
    localctx
    0.75
    Activations Density 0.160%

    No Known Activations