© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 8481
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical models, simulation parameters, and optimization processes

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    yelitis
    -0.53
    Autoritní
    -0.51
    ूरत
    -0.49
    ElementException
    -0.48
     superflu
    -0.48
    omiast
    -0.46
    argout
    -0.46
    ORIGIN
    -0.45
    γγε
    -0.45
    unisex
    -0.45
    POSITIVE LOGITS
    
    0.75
     possibilities
    0.65
     Investig
    0.64
     possibility
    0.60
     dAtA
    0.57
     itertools
    0.55
     possibilités
    0.55
     experiment
    0.55
     posibilidades
    0.54
     trial
    0.54
    Activations Density 1.154%

    No Known Activations