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. 3-GEMMASCOPE-RES-16K
    6. 6218
    Prev
    Next
    INDEX
    Explanations

    terms related to data persistence and state 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 @ 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
    tagHelper
    -0.98
    ScopeManager
    -0.90
    AddTagHelper
    -0.86
    ImageContext
    -0.77
    jspx
    -0.75
    sidemargin
    -0.75
    PageContext
    -0.69
     oka
    -0.68
    VersionUID
    -0.68
    sizeCache
    -0.67
    POSITIVE LOGITS
    Mvc
    1.47
     Initialized
    1.04
    </thead>
    1.02
    __':
    0.81
    nestjs
    0.78
    persistence
    0.73
    mvc
    0.71
    GetMapping
    0.70
     AssemblyTitle
    0.68
    __":
    0.68
    Activations Density 0.007%

    No Known Activations