© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1653
    Prev
    Next
    INDEX
    Explanations

    terms related to 'reserve' in various contexts, such as banking or allocation

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

    "Reserve" or "reserved" followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    reserve currency, words, constituency, shift, prisons

    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
    RuleContext
    -0.83
     فريبيس
    -0.62
    Географиясе
    -0.60
     kasarigan
    -0.59
    GEBURTSDATUM
    -0.59
    حوالہ
    -0.58
     EconPapers
    -0.57
    queryInterface
    -0.54
    Vidite
    -0.54
    Naissance
    -0.54
    POSITIVE LOGITS
    RESERV
    0.96
     RESERV
    0.94
     Reserve
    0.89
     Reserves
    0.84
     Reserv
    0.84
     RESERVE
    0.82
    Reserv
    0.81
     reserves
    0.80
    Reserve
    0.80
     reserve
    0.78
    Activations Density 0.207%

    No Known Activations