© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86165
    Prev
    Next
    INDEX
    Explanations

    occurrences of "MemoryWarning" in code

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

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     add
    -0.35
     co
    -0.33
     проводить
    -0.32
    add
    -0.31
     Union
    -0.31
     União
    -0.30
     stuff
    -0.30
     عباس
    -0.29
    Add
    -0.29
     do
    -0.29
    POSITIVE LOGITS
    MemoryWarning
    7.31
     viewDidLoad
    1.43
    Personensuche
    1.31
     NSCoder
    1.29
    parsedMessage
    1.21
    Personendaten
    1.18
     للاسماء
    1.18
    MigrationBuilder
    1.13
    WriteBarrier
    1.10
     يتيمه
    1.09
    Activations Density 0.000%

    No Known Activations