© 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. 3-GEMMASCOPE-RES-16K
    11. 13011
    Prev
    Next
    INDEX
    Explanations

    terms related to 'ash' and its various mentions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.95
    setVerticalGroup
    -0.89
    "?>
    -0.88
    DateTimeField
    -0.87
    
    -0.87
     disambiguazione
    -0.86
     propOrder
    -0.86
    MemoryWarning
    -0.85
    MessageTagHelper
    -0.83
     FetchType
    -0.83
    POSITIVE LOGITS
     Ash
    3.38
    Ash
    3.10
     ash
    2.96
    ash
    2.41
     ASH
    2.36
    ASH
    2.02
     ashes
    1.89
    ashes
    1.43
    Ashlee
    1.39
    ashing
    1.35
    Activations Density 0.078%

    No Known Activations