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. 5-GEMMASCOPE-RES-16K
    6. 3488
    Prev
    Next
    INDEX
    Explanations

    occurrences of package declarations and potential copyright information in source code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.79
     estudar
    -0.72
     AssemblyTitle
    -0.65
    ElementException
    -0.65
     variés
    -0.63
     adicionais
    -0.57
     réguli
    -0.56
    enterOuterAlt
    -0.56
     >=",
    -0.55
    #+#
    -0.54
    POSITIVE LOGITS
     com
    1.51
     Com
    1.15
    Com
    1.02
    com
    1.01
     COM
    0.86
    COM
    0.81
     BorderRadius
    0.78
     comm
    0.72
     الاطلاع
    0.71
     Comm
    0.66
    Activations Density 0.023%

    No Known Activations