© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27908
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations related to concepts and their contexts

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

    defines and is defined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geslacht
    -0.57
     Walkover
    -0.51
    Espero
    -0.46
    Pranala
    -0.46
     transfer
    -0.45
     cucchia
    -0.43
     Transfer
    -0.43
    ConfigureAwait
    -0.42
    zsche
    -0.42
     routing
    -0.41
    POSITIVE LOGITS
     definition
    1.63
     definitions
    1.49
    definition
    1.38
     Definition
    1.35
     Definitions
    1.31
     defined
    1.20
     Defining
    1.19
    Defining
    1.16
    定義
    1.16
    Definition
    1.14
    Activations Density 0.148%

    No Known Activations