© 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-2-2B
    7. Residual Stream - 65k
    9. 12-GEMMASCOPE-RES-65K
    11. 13543
    Prev
    Next
    INDEX
    Explanations

    terms related to semantics and their accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.98
    oporosis
    -0.85
     propOrder
    -0.81
    دانشنامهٔ
    -0.81
     JADX
    -0.81
    AutoScaleMode
    -0.77
     OPP
    -0.74
    ///</
    -0.74
    floxacin
    -0.74
    ografija
    -0.73
    POSITIVE LOGITS
    Semantics
    1.24
     Semantics
    1.07
     Semantic
    1.07
     semantics
    1.02
     semantic
    1.00
    semantic
    0.97
    Semantic
    0.93
    seman
    0.88
    semantics
    0.86
     SEM
    0.84
    Activations Density 0.004%

    No Known Activations