© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11539
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and operations in programming, particularly in the context of databases and data tables

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

    Often precedes code snippets or unusual text

    np_acts-logits-general · gemini-2.0-flash

    iterate through lists

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Normdatei
    -0.87
     >=",
    -0.83
    RectangleBorder
    -0.80
     raiſ
    -0.80
     pinulongan
    -0.79
    TagHelper
    -0.75
    AnchorStyles
    -0.75
     faſt
    -0.74
    DockStyle
    -0.72
    +#+#
    -0.72
    POSITIVE LOGITS
     saites
    0.53
     un
    0.49
     no
    0.44
     iz
    0.44
    artifactId
    0.42
     note
    0.42
     ie
    0.42
     թվական
    0.42
     manifestazione
    0.40
     let
    0.39
    Activations Density 0.014%

    No Known Activations