© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9844
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to stochastic processes and mathematical structures in statistics

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

    mathematical and computer science technical terms such as vector spaces, arrays, Markov chains, Lévy processes, and hash functions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    исленность
    -0.49
    DockStyle
    -0.46
     pinulongan
    -0.43
     vertical
    -0.40
     green
    -0.40
     early
    -0.40
     Vertical
    -0.38
    Guil
    -0.38
    GIVEREF
    -0.37
    +#+#
    -0.37
    POSITIVE LOGITS
    Rhestr
    0.60
    Personensuche
    0.59
    parsedMessage
    0.53
     jsonArray
    0.53
     InputDecoration
    0.52
    ยนต์
    0.50
     GenerationType
    0.49
     ArrayAdapter
    0.49
     ब्रेकडाउन
    0.49
    crollView
    0.49
    Activations Density 0.898%

    No Known Activations