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. 2-GEMMASCOPE-RES-16K
    6. 6231
    Prev
    Next
    INDEX
    Explanations

    code elements related to type and assembly management in programming

    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
     Efq
    -0.96
     فريبيس
    -0.93
     Theſe
    -0.92
    rungsseite
    -0.92
     itſelf
    -0.91
    principalColumn
    -0.90
     myſelf
    -0.88
    principalTable
    -0.86
    IsMutable
    -0.83
     becauſe
    -0.82
    POSITIVE LOGITS
     «
    0.47
     T
    0.44
     da
    0.43
      
    0.43
    ole
    0.42
     Be
    0.41
     Lee
    0.41
     dan
    0.41
     transfer
    0.40
     so
    0.40
    Activations Density 0.257%

    No Known Activations