© 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. 18-GEMMASCOPE-RES-16K
    11. 2985
    Prev
    Next
    INDEX
    Explanations

    references to specific times or timestamps

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

    Times with am or pm

    np_acts-logits-general · gemini-2.0-flash

    specific times of day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.69
     InputDecoration
    -0.57
     &___
    -0.53
    Sprintf
    -0.51
    yskland
    -0.50
     createState
    -0.49
    épend
    -0.47
     Carthage
    -0.47
     noqa
    -0.47
     AssemblyCulture
    -0.47
    POSITIVE LOGITS
     विश्वसनीयता
    0.62
     today
    0.59
     tadi
    0.57
    Revenir
    0.56
     сегодняш
    0.54
    uxxxx
    0.54
    CloseOperation
    0.53
     Sade
    0.52
     الدولى
    0.52
    PathVariable
    0.50
    Activations Density 0.171%

    No Known Activations