© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13949
    Prev
    Next
    INDEX
    Explanations

    numerical values and operations

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

    Numbers or symbols following other numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and code snippets

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     CreateTagHelper
    -0.49
    原始内容存档于
    -0.38
     eletrônico
    -0.37
    IntoConstraints
    -0.37
     inoxydable
    -0.36
    
    -0.34
    multirow
    -0.34
     Mujer
    -0.33
    Trichloroethane
    -0.33
     HasFactory
    -0.33
    POSITIVE LOGITS
     contextLoads
    0.55
    parsedMessage
    0.55
    AutoField
    0.53
    VGND
    0.48
    CppCodeGen
    0.46
     kiin
    0.46
    dollis
    0.45
    Bened
    0.45
    RuntimeObject
    0.44
     insignificant
    0.44
    Activations Density 1.487%

    No Known Activations