© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3427
    Prev
    Next
    INDEX
    Explanations

    elements related to data manipulation and programming syntax

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

    nested loop structures with bracket and parenthesis indexing operations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.59
     CreateTagHelper
    -0.53
    
    -0.51
    complexContent
    -0.49
     neceff
    -0.44
     disponibilités
    -0.43
    carina
    -0.42
     للمعارف
    -0.41
    Посилання
    -0.41
    SpringBootTest
    -0.41
    POSITIVE LOGITS
     column
    2.28
     columns
    2.16
     Columns
    1.81
     Column
    1.81
    column
    1.80
     columnas
    1.75
     columna
    1.71
     COLUMN
    1.66
    Column
    1.65
     coluna
    1.61
    Activations Density 0.245%

    No Known Activations