© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 45492
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms and components associated with software development, particularly Makefiles

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

    Makefile and "do" words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bahía
    -0.52
     CURIAM
    -0.49
     poitrine
    -0.48
     referenties
    -0.47
    Šaltiniai
    -0.47
     logistique
    -0.46
    uerdo
    -0.46
     bandeira
    -0.45
    waltung
    -0.45
    anskje
    -0.44
    POSITIVE LOGITS
     làm
    2.20
     Làm
    1.66
    Làm
    1.53
    làm
    1.52
    ทำ
    0.95
     ทำ
    0.79
    作
    0.67
    做
    0.67
     做
    0.66
     lm
    0.66
    Activations Density 0.001%

    No Known Activations