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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1263
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming mechanics and strategies

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

    game mechanics and player strategy elements

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

    programming or technical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fictional
    -0.53
     official
    -0.51
    CONCURRENT
    -0.46
     immagin
    -0.45
     fictitious
    -0.43
    Ừ
    -0.43
    ComponentName
    -0.43
     sortes
    -0.43
     unpublished
    -0.43
    newest
    -0.42
    POSITIVE LOGITS
    OGND
    0.87
     initComponents
    0.81
     propOrder
    0.71
     offensively
    0.71
    FormTagHelper
    0.69
    ValueGeneration
    0.68
     useContext
    0.67
     defensively
    0.67
     chi̍t
    0.66
     MainAxisSize
    0.66
    Activations Density 0.037%

    No Known Activations