© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 5236
    Prev
    Next
    INDEX
    Explanations

    structured data related to software dependencies and configurations

    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
     wacht
    -0.47
     setPrice
    -0.46
    inigungs
    -0.44
     hot
    -0.44
    坐
    -0.43
     testified
    -0.43
     healing
    -0.42
    Joined
    -0.41
     zase
    -0.41
    writerow
    -0.41
    POSITIVE LOGITS
     تضيفلها
    0.93
     typelib
    0.79
    SpringBootTest
    0.79
    Autowired
    0.78
     Theſe
    0.76
    TagMode
    0.75
     fubject
    0.73
     occaf
    0.73
    HtmlAttribute
    0.72
    OGND
    0.71
    Activations Density 3.411%

    No Known Activations