Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10869
    Prev
    Next
    INDEX
    Explanations

    programming commands and control flow statements

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

    Code, commands, or identifiers

    np_acts-logits-general · gemini-2.0-flash

    characterization of novel alleles

    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
     hende
    -0.49
    خاذ
    -0.39
    物を
    -0.39
    ھی
    -0.39
     zich
    -0.38
     camas
    -0.37
    ExecuteNonQuery
    -0.37
    Request
    -0.37
     szé
    -0.37
     sorella
    -0.37
    POSITIVE LOGITS
     مشين
    1.08
    AddTagHelper
    0.99
     <<<<<<<<<<<<<<
    0.96
    MigrationBuilder
    0.93
     surla
    0.90
    
    0.85
    rungsseite
    0.84
    RegressionTest
    0.83
    IndentedString
    0.82
     дописавши
    0.81
    Activations Density 0.182%

    No Known Activations