© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 97281
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ClientSize
    -0.51
    cons
    -0.26
    ];
    -0.26
    ");
    -0.25
     piece
    -0.25
    mod
    -0.24
     phase
    -0.24
    back
    -0.24
    จัง
    -0.23
    __.__
    -0.23
    POSITIVE LOGITS
     DbSet
    2.94
     насељу
    2.30
    GeoNames
    1.57
     ObjectParameter
    0.98
     Chwiliwch
    0.94
    
    0.90
     kasarigan
    0.89
    httphttps
    0.89
    rungsseite
    0.88
     initComponents
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.