© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 41009
    Prev
    Next
    INDEX
    Explanations

    technical terms related to file systems or data structures in programming

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

    inorganic N and inode structures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Administrativna
    -0.63
    PhysRevD
    -0.62
     témoig
    -0.61
     propOrder
    -0.60
    tagHelper
    -0.60
    GenerationType
    -0.58
    पया
    -0.58
     kasarigan
    -0.58
     queſta
    -0.58
    ValueStyle
    -0.57
    POSITIVE LOGITS
    In
    0.79
     In
    0.75
     IN
    0.70
    in
    0.69
     in
    0.66
    IN
    0.65
    inFile
    0.63
    isIn
    0.62
     Inoue
    0.60
    ino
    0.55
    Activations Density 0.037%

    No Known Activations