© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12127
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.00
     AssemblyCompany
    -0.90
    iſche
    -0.89
     imagui
    -0.88
    ſſung
    -0.88
    <unused68>
    -0.87
    <unused16>
    -0.87
    <unused23>
    -0.87
    <pad>
    -0.86
    [@BOS@]
    -0.86
    POSITIVE LOGITS
    1
    0.48
     
    0.47
    ;
    0.45
        
    0.45
    ↵
    0.44
     $
    0.43
    2
    0.43
    4
    0.41
    .
    0.41
    3
    0.41
    Activations Density 0.557%

    No Known Activations