© 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. 2-GEMMASCOPE-RES-16K
    6. 16320
    Prev
    Next
    INDEX
    Explanations

    instances of the word "empty."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     akik
    -0.56
    くる
    -0.54
     wacht
    -0.54
     gesuchten
    -0.53
     Роб
    -0.52
    mate
    -0.52
     Grady
    -0.52
     isolato
    -0.52
     redou
    -0.51
     affaires
    -0.50
    POSITIVE LOGITS
     è
    1.89
     sono
    1.49
     È
    1.25
     Sono
    1.22
    Sono
    1.18
    __":
    
    1.10
    __':
    1.09
    sono
    1.08
    __':
    
    1.06
    __":
    1.05
    Activations Density 0.051%

    No Known Activations