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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 103089
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to justice and court proceedings

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

    of proof, recent, ensuing, certiorari

    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
     szczeg
    -0.29
     cuchara
    -0.28
     Arbeitnehmer
    -0.27
     gelieb
    -0.26
    arbit
    -0.26
     tilgjenge
    -0.26
     Kı
    -0.26
    Reino
    -0.25
     szczegó
    -0.24
    LEGGI
    -0.24
    POSITIVE LOGITS
    featureID
    0.56
     kasarigan
    0.55
    SharedCtor
    0.55
     noDo
    0.54
     становника
    0.52
    󠁿
    0.51
    EFAULT
    0.50
     deci
    0.50
    endregion
    0.50
    sizeCache
    0.49
    Activations Density 0.205%

    No Known Activations