Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3370
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     f
    -0.58
     t
    -0.58
     
    -0.56
    <eos>
    -0.55
     player
    -0.53
    ↵↵
    -0.51
     o
    -0.51
     O
    -0.50
     my
    -0.48
     file
    -0.47
    POSITIVE LOGITS
     itſelf
    1.13
     myſelf
    1.12
     مشين
    1.10
     Shakspeare
    1.04
    
    1.04
     purpoſe
    1.02
     متعلقه
    1.02
     Мексичка
    0.99
     ſeveral
    0.98
     pleaſure
    0.97
    Activations Density 0.334%

    No Known Activations