© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10005
    Prev
    Next
    INDEX
    Explanations

    references to the current state or conditions in various contexts

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

    "present" or "previous" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    current or previous state

    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
     vroeger
    -0.72
     varandra
    -0.70
     Мексичка
    -0.68
     prochaines
    -0.67
     ägg
    -0.65
     atualmente
    -0.65
     techniczne
    -0.65
     parteci
    -0.65
    exitRule
    -0.64
    CrossRef
    -0.63
    POSITIVE LOGITS
     version
    0.86
     generation
    0.77
     iteration
    0.77
     situation
    0.74
     incarnation
    0.72
     edition
    0.69
     versions
    0.67
     setup
    0.65
     batch
    0.63
     regime
    0.62
    Activations Density 0.400%

    No Known Activations