© 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. 58919
    Prev
    Next
    INDEX
    Explanations

    keywords related to encoding and decoding processes

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

    encoding data

    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
    (!_
    -0.49
    iiiiiiii
    -0.47
    tanleria
    -0.46
    AsUp
    -0.44
    tij
    -0.44
    windowFixed
    -0.42
    DotNetBar
    -0.42
    FontOfSize
    -0.42
    gartner
    -0.42
     resultList
    -0.42
    POSITIVE LOGITS
     encode
    1.23
    encode
    1.21
    Encode
    1.14
     encoding
    1.08
     Encode
    1.07
     encodes
    1.04
     Encoding
    1.01
    encoding
    0.93
    encoded
    0.93
     encoded
    0.91
    Activations Density 0.016%

    No Known Activations