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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 38615
    Prev
    Next
    INDEX
    Explanations

    instances of the word "relief" in various contexts related to legal matters

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

    relief sought

    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
    qvarna
    -0.54
    yarnpkg
    -0.45
    odacty
    -0.44
    Manager
    -0.44
     Commodore
    -0.43
    MouseButton
    -0.43
     Tarragona
    -0.42
    UNIVERSIDAD
    -0.42
     Lond
    -0.42
     astronomer
    -0.42
    POSITIVE LOGITS
     relief
    2.59
    relief
    2.44
     Relief
    2.41
    Relief
    2.28
     RELIEF
    2.27
     reliefs
    1.79
     alivio
    1.65
     relieve
    1.59
     relieved
    1.52
     relieves
    1.45
    Activations Density 0.008%

    No Known Activations