© 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. 35119
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases and evaluations of places or experiences, particularly regarding quality and features

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

    added bonus / lack of

    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
     EconPapers
    -0.82
     المعيارى
    -0.80
     ब्रेकडाउन
    -0.74
    setVerticalGroup
    -0.74
    TagMode
    -0.72
    clerView
    -0.70
     ſche
    -0.67
     يتيمه
    -0.66
    AutoField
    -0.66
     Chwiliwch
    -0.66
    POSITIVE LOGITS
      
    0.30
     bowiem
    0.27
    }{*}{
    0.26
     pavillon
    0.26
     infatti
    0.26
          
    0.26
    ↵
    0.25
     EdgeInsets
    0.25
     honra
    0.24
    }{\
    0.23
    Activations Density 0.046%

    No Known Activations