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. 3907
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and security exceptions

    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
    SharedDtor
    -1.14
     мәкал
    -1.14
     propOrder
    -1.09
     مشين
    -1.07
    IVEREF
    -1.04
    WithIOException
    -1.03
     EconPapers
    -0.96
    AddHtmlAttribute
    -0.94
    AccessorTable
    -0.93
    fjspx
    -0.90
    POSITIVE LOGITS
    輩
    0.47
     отношению
    0.44
    â
    0.43
     v
    0.40
     fore
    0.39
    schul
    0.39
     vo
    0.39
    than
    0.38
    ´
    0.38
     were
    0.38
    Activations Density 0.079%

    No Known Activations