© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 31662
    Prev
    Next
    INDEX
    Explanations

    the use of assignment operators and their associated data structures in programming code

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

    <start_of_turn>user code snippets

    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
     betweenstory
    -0.66
    évaluateur
    -0.63
     $_-
    -0.62
    <unused28>
    -0.61
    <unused47>
    -0.61
    <unused52>
    -0.61
    <unused68>
    -0.61
    <unused41>
    -0.61
    <unused8>
    -0.61
    <unused14>
    -0.61
    POSITIVE LOGITS
    Referanser
    0.47
    providedIn
    0.42
     خارجية
    0.35
    Enllaços
    0.35
    InjectMocks
    0.33
    runApp
    0.31
    GIVEREF
    0.30
    setContentView
    0.29
    RunWith
    0.29
    ])]
    0.28
    Activations Density 0.018%

    No Known Activations