© 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. 20-GEMMASCOPE-RES-65K
    11. 608
    Prev
    Next
    INDEX
    Explanations

    references to indexing or accessing elements in data structures

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

    occurrences of the variable "i" and structures related to input-output operations in code

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

    code syntax with brackets

    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
     [
    -0.63
    sum
    -0.51
     on
    -0.48
    de
    -0.47
    te
    -0.46
     az
    -0.46
    GA
    -0.46
    [
    -0.45
     sum
    -0.45
    ola
    -0.45
    POSITIVE LOGITS
     незавершена
    1.19
     itſelf
    1.11
     myſelf
    1.09
     autorytatywna
    1.06
     CreateTagHelper
    1.04
    ^(@)
    1.02
     reaſon
    1.01
     themſelves
    1.00
    ſelves
    1.00
    ThroughAttribute
    1.00
    Activations Density 0.010%

    No Known Activations