© 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. 5-GEMMASCOPE-RES-16K
    11. 9654
    Prev
    Next
    INDEX
    Explanations

    references to knives and their associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.87
     Nellie
    -0.83
     Recre
    -0.77
     NOL
    -0.74
     getResources
    -0.74
     Seymour
    -0.74
     Nelly
    -0.73
    mnop
    -0.72
     sembl
    -0.72
    躇
    -0.71
    POSITIVE LOGITS
     knife
    1.59
     knives
    1.42
     blades
    1.38
     blade
    1.32
     Knife
    1.31
    knife
    1.25
     slice
    1.24
     Knives
    1.24
    blade
    1.22
    Knife
    1.22
    Activations Density 0.116%

    No Known Activations