© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8272
    Prev
    Next
    INDEX
    Explanations

    the word "essential" and variations of it, indicating a focus on critical elements or requirements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "[something] is essential for"

    np_acts-logits-general · gemini-2.0-flash

    essential for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.59
    homonymie
    -0.59
    ScopeManager
    -0.59
     CreateTagHelper
    -0.58
    RuleContext
    -0.57
    PRNewswire
    -0.56
    titleMargin
    -0.54
     ApiException
    -0.52
     Substantial
    -0.52
    ArrowToggle
    -0.52
    POSITIVE LOGITS
     ingredient
    0.95
     components
    0.94
     elements
    0.91
     ingredients
    0.91
     component
    0.88
     element
    0.84
     prerequisite
    0.78
     Ingredient
    0.78
     Voraussetzung
    0.77
     parts
    0.75
    Activations Density 0.195%

    No Known Activations