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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12383
    Prev
    Next
    INDEX
    Explanations

    operations related to bit-shifting in programming code

    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
     Groen
    -0.58
    RAHAM
    -0.58
    Corn
    -0.57
    Toponymie
    -0.57
    复制代码
    -0.55
     Horv
    -0.54
     corn
    -0.53
    Anhalt
    -0.50
    SequentialGroup
    -0.49
    ёх
    -0.49
    POSITIVE LOGITS
     <<
    2.94
    <<
    2.51
    )<<
    2.00
    ]<<
    1.94
    <<<
    1.75
    ()<<
    1.70
     <<=
    1.68
    <<"
    1.65
    <<(
    1.64
    <<<<
    1.58
    Activations Density 0.032%

    No Known Activations